trim will happen before audio processor

frontend: Keep screen awake and scroll down when transcribing.

CONTRIBUTING.md

@@ -15,7 +15,7 @@ Thank you for considering contributing ! We appreciate your time and effort to h
 
 ## Opening Issues
 
-If you encounter a problem with diart or want to suggest an improvement, please follow these guidelines when opening an issue:
+If you encounter a problem with WhisperLiveKit or want to suggest an improvement, please follow these guidelines when opening an issue:
 
 - **Bug Reports:**
   - Clearly describe the error. **Please indicate the parameters you use, especially the model(s)**
@@ -43,4 +43,4 @@ We welcome and appreciate contributions! To ensure a smooth review process, plea
 
 ## Thank You
 
-Your contributions make diart better for everyone. Thank you for your time and dedication!
+Your contributions make WhisperLiveKit better for everyone. Thank you for your time and dedication!

Dockerfile

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:12.8.1-cudnn-runtime-ubuntu22.04
+FROM nvidia/cuda:12.9.1-cudnn-devel-ubuntu24.04
 
 ENV DEBIAN_FRONTEND=noninteractive
 ENV PYTHONUNBUFFERED=1
@@ -9,24 +9,20 @@ ARG EXTRAS
 ARG HF_PRECACHE_DIR
 ARG HF_TKN_FILE
 
-# Install system dependencies
-#RUN apt-get update && \
-#    apt-get install -y ffmpeg git && \
-#    apt-get clean && \
-#    rm -rf /var/lib/apt/lists/*
-
-# 2) Install system dependencies + Python + pip
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
         python3 \
         python3-pip \
+        python3-venv \
         ffmpeg \
         git \
         build-essential \
         python3-dev && \
     rm -rf /var/lib/apt/lists/*
 
-RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu129
 
 COPY . .
 
@@ -35,10 +31,10 @@ COPY . .
 #         for more details.
 RUN if [ -n "$EXTRAS" ]; then \
       echo "Installing with extras: [$EXTRAS]"; \
-      pip install --no-cache-dir .[$EXTRAS]; \
+      pip install --no-cache-dir whisperlivekit[$EXTRAS]; \
     else \
       echo "Installing base package only"; \
-      pip install --no-cache-dir .; \
+      pip install --no-cache-dir whisperlivekit; \
     fi
 
 # Enable in-container caching for Hugging Face models by: 
@@ -81,4 +77,4 @@ EXPOSE 8000
 ENTRYPOINT ["whisperlivekit-server", "--host", "0.0.0.0"]
 
 # Default args
-CMD ["--model", "tiny.en"]
+CMD ["--model", "medium"]

Dockerfile.cpu

@@ -0,0 +1,61 @@
+FROM python:3.13-slim
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+ARG EXTRAS
+ARG HF_PRECACHE_DIR
+ARG HF_TKN_FILE
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        ffmpeg \
+        git \
+        build-essential \
+        python3-dev && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install CPU-only PyTorch
+RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+
+COPY . .
+
+# Install WhisperLiveKit directly, allowing for optional dependencies
+RUN if [ -n "$EXTRAS" ]; then \
+      echo "Installing with extras: [$EXTRAS]"; \
+      pip install --no-cache-dir whisperlivekit[$EXTRAS]; \
+    else \
+      echo "Installing base package only"; \
+      pip install --no-cache-dir whisperlivekit; \
+    fi
+
+# Enable in-container caching for Hugging Face models
+VOLUME ["/root/.cache/huggingface/hub"]
+
+# Conditionally copy a local pre-cache from the build context
+RUN if [ -n "$HF_PRECACHE_DIR" ]; then \
+      echo "Copying Hugging Face cache from $HF_PRECACHE_DIR"; \
+      mkdir -p /root/.cache/huggingface/hub && \
+      cp -r $HF_PRECACHE_DIR/* /root/.cache/huggingface/hub; \
+    else \
+      echo "No local Hugging Face cache specified, skipping copy"; \
+    fi
+
+# Conditionally copy a Hugging Face token if provided
+RUN if [ -n "$HF_TKN_FILE" ]; then \
+      echo "Copying Hugging Face token from $HF_TKN_FILE"; \
+      mkdir -p /root/.cache/huggingface && \
+      cp $HF_TKN_FILE /root/.cache/huggingface/token; \
+    else \
+      echo "No Hugging Face token file specified, skipping token setup"; \
+    fi
+    
+# Expose port for the transcription server
+EXPOSE 8000
+
+ENTRYPOINT ["whisperlivekit-server", "--host", "0.0.0.0"]
+
+# Default args - you might want to use a smaller model for CPU
+CMD ["--model", "tiny"]

README.md

@@ -4,128 +4,104 @@
 <img src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/demo.png" alt="WhisperLiveKit Demo" width="730">
 </p>
 
-<p align="center"><b>Real-time, Fully Local Speech-to-Text with Speaker Diarization</b></p>
+<p align="center"><b>Real-time, Fully Local Speech-to-Text with Speaker Identification</b></p>
 
 <p align="center">
 <a href="https://pypi.org/project/whisperlivekit/"><img alt="PyPI Version" src="https://img.shields.io/pypi/v/whisperlivekit?color=g"></a>
-<a href="https://pepy.tech/project/whisperlivekit"><img alt="PyPI Downloads" src="https://static.pepy.tech/personalized-badge/whisperlivekit?period=total&units=international_system&left_color=grey&right_color=brightgreen&left_text=downloads"></a>
+<a href="https://pepy.tech/project/whisperlivekit"><img alt="PyPI Downloads" src="https://static.pepy.tech/personalized-badge/whisperlivekit?period=total&units=international_system&left_color=grey&right_color=brightgreen&left_text=installations"></a>
 <a href="https://pypi.org/project/whisperlivekit/"><img alt="Python Versions" src="https://img.shields.io/badge/python-3.9--3.13-dark_green"></a>
 <a href="https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/License-MIT/Dual Licensed-dark_green"></a>
 </p>
 
-Built on [WhisperStreaming](https://github.com/ufal/whisper_streaming) and [SimulStreaming](https://github.com/ufal/SimulStreaming), WhisperLiveKit provides real-time speech transcription in your browser, with a ready-to-use backend and a simple, customizable frontend. ✨
+
+Real-time speech transcription directly to your browser, with a ready-to-use backend+server and a simple frontend. ✨
+
+#### Powered by Leading Research:
+
+- [SimulStreaming](https://github.com/ufal/SimulStreaming) (SOTA 2025) - Ultra-low latency transcription with AlignAtt policy
+- [WhisperStreaming](https://github.com/ufal/whisper_streaming) (SOTA 2023) - Low latency transcription with LocalAgreement policy
+- [Streaming Sortformer](https://arxiv.org/abs/2507.18446) (SOTA 2025) - Advanced real-time speaker diarization
+- [Diart](https://github.com/juanmc2005/diart) (SOTA 2021) - Real-time speaker diarization
+- [Silero VAD](https://github.com/snakers4/silero-vad) (2024) - Enterprise-grade Voice Activity Detection
 
 
-### Key Features
+> **Why not just run a simple Whisper model on every audio batch?** Whisper is designed for complete utterances, not real-time chunks. Processing small segments loses context, cuts off words mid-syllable, and produces poor transcription. WhisperLiveKit uses state-of-the-art simultaneous speech research for intelligent buffering and incremental processing.
 
-- **Real-time Transcription** - Locally (or on-prem) convert speech to text instantly as you speak
-- **Speaker Diarization** - Identify different speakers in real-time using [Diart](https://github.com/juanmc2005/diart)
-- **Multi-User Support** - Handle multiple users simultaneously with a single backend/server
-- **Automatic Silence Chunking** – Automatically chunks when no audio is detected to limit buffer size
-- **Confidence Validation** – Immediately validate high-confidence tokens for faster inference (WhisperStreaming only)
-- **Buffering Preview** – Displays unvalidated transcription segments (not compatible with SimulStreaming yet)
-- **Punctuation-Based Speaker Splitting [BETA]** - Align speaker changes with natural sentence boundaries for more readable transcripts
-- **SimulStreaming Backend** - [Dual-licensed](https://github.com/ufal/SimulStreaming#-licence-and-contributions) - Ultra-low latency transcription using SOTA AlignAtt policy. 
 
 ### Architecture
 
-<img alt="Architecture" src="architecture.png" />
+<img alt="Architecture" src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/architecture.png" />
 
+*The backend supports multiple concurrent users. Voice Activity Detection reduces overhead when no voice is detected.*
 
-## Quick Start
+### Installation & Quick Start
 
 ```bash
-# Install the package
 pip install whisperlivekit
-
-# Start the transcription server
-whisperlivekit-server --model tiny.en
-
-# Open your browser at http://localhost:8000 to see the interface.
-# Use  -ssl-certfile public.crt --ssl-keyfile private.key parameters to use SSL
 ```
 
-That's it! Start speaking and watch your words appear on screen.
+>  **FFmpeg is required** and must be installed before using WhisperLiveKit
+> 
+> | OS | How to install |
+> |-----------|-------------|
+>  | Ubuntu/Debian | `sudo apt install ffmpeg` |
+> | MacOS | `brew install ffmpeg` |
+> | Windows | Download .exe from https://ffmpeg.org/download.html and add to PATH |
 
-## Installation
+#### Quick Start
+1. **Start the transcription server:**
+   ```bash
+   whisperlivekit-server --model base --language en
+   ```
 
-```bash
-#Install from PyPI (Recommended)
-pip install whisperlivekit
+2. **Open your browser** and navigate to `http://localhost:8000`. Start speaking and watch your words appear in real-time!
 
-#Install from Source
-git clone https://github.com/QuentinFuxa/WhisperLiveKit
-cd WhisperLiveKit
-pip install -e .
-```
 
-### FFmpeg Dependency
+> - See [tokenizer.py](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py) for the list of all available languages.
+> - For HTTPS requirements, see the **Parameters** section for SSL configuration options.
 
-```bash
-# Ubuntu/Debian
-sudo apt install ffmpeg
+ 
 
-# macOS
-brew install ffmpeg
+#### Optional Dependencies
 
-# Windows
-# Download from https://ffmpeg.org/download.html and add to PATH
-```
+| Optional | `pip install` |
+|-----------|-------------|
+| Speaker diarization with Sortformer | `git+https://github.com/NVIDIA/NeMo.git@main#egg=nemo_toolkit[asr]` |
+| Speaker diarization with Diart | `diart` |
+| Original Whisper backend | `whisper` |
+| Improved timestamps backend | `whisper-timestamped` |
+| Apple Silicon optimization backend | `mlx-whisper` |
+| OpenAI API backend | `openai` |
 
-### Optional Dependencies
+See  **Parameters & Configuration** below on how to use them.
 
-```bash
-# Voice Activity Controller (prevents hallucinations)
-pip install torch
-
-# Sentence-based buffer trimming
-pip install mosestokenizer wtpsplit
-pip install tokenize_uk  # If you work with Ukrainian text
-
-# Speaker diarization
-pip install diart
-
-# Alternative Whisper backends (default is faster-whisper)
-pip install whisperlivekit[whisper]              # Original Whisper
-pip install whisperlivekit[whisper-timestamped]  # Improved timestamps
-pip install whisperlivekit[mlx-whisper]          # Apple Silicon optimization
-pip install whisperlivekit[openai]               # OpenAI API
-pip install whisperlivekit[simulstreaming]
-```
-
-### 🎹 Pyannote Models Setup
-
-For diarization, you need access to pyannote.audio models:
-
-1. [Accept user conditions](https://huggingface.co/pyannote/segmentation) for the `pyannote/segmentation` model
-2. [Accept user conditions](https://huggingface.co/pyannote/segmentation-3.0) for the `pyannote/segmentation-3.0` model
-3. [Accept user conditions](https://huggingface.co/pyannote/embedding) for the `pyannote/embedding` model
-4. Login with HuggingFace:
-```bash
-pip install huggingface_hub
-huggingface-cli login
-```
+ 
+> **Pyannote Models Setup** For diarization, you need access to pyannote.audio models:
+> 1. [Accept user conditions](https://huggingface.co/pyannote/segmentation) for the `pyannote/segmentation` model
+> 2. [Accept user conditions](https://huggingface.co/pyannote/segmentation-3.0) for the `pyannote/segmentation-3.0` model
+> 3. [Accept user conditions](https://huggingface.co/pyannote/embedding) for the `pyannote/embedding` model
+>4. Login with HuggingFace:
+> ```bash
+> huggingface-cli login
+> ```
 
 ## 💻 Usage Examples
 
-### Command-line Interface
+#### Command-line Interface
 
 Start the transcription server with various options:
 
 ```bash
-# Basic server with English model
-whisperlivekit-server --model tiny.en
+# Use better model than default (small)
+whisperlivekit-server --model large-v3
 
-# Advanced configuration with diarization
-whisperlivekit-server --host 0.0.0.0 --port 8000 --model medium --diarization --language auto
-
-# SimulStreaming backend for ultra-low latency
-whisperlivekit-server --backend simulstreaming --model large-v3 --frame-threshold 20
+# Advanced configuration with diarization and language
+whisperlivekit-server --host 0.0.0.0 --port 8000 --model medium --diarization --language fr
 ```
 
 
-### Python API Integration (Backend)
-Check [basic_server.py](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/basic_server.py) for a complete example.
+#### Python API Integration (Backend)
+Check [basic_server](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/basic_server.py) for a more complete example of how to use the functions and classes.
 
 ```python
 from whisperlivekit import TranscriptionEngine, AudioProcessor, parse_args
@@ -140,14 +116,10 @@ transcription_engine = None
 async def lifespan(app: FastAPI):
     global transcription_engine
     transcription_engine = TranscriptionEngine(model="medium", diarization=True, lan="en")
-    # You can also load from command-line arguments using parse_args()
-    # args = parse_args()
-    # transcription_engine = TranscriptionEngine(**vars(args))
     yield
 
 app = FastAPI(lifespan=lifespan)
 
-# Process WebSocket connections
 async def handle_websocket_results(websocket: WebSocket, results_generator):
     async for response in results_generator:
         await websocket.send_json(response)
@@ -167,43 +139,46 @@ async def websocket_endpoint(websocket: WebSocket):
         await audio_processor.process_audio(message)        
 ```
 
-### Frontend Implementation
+#### Frontend Implementation
 
-The package includes a simple HTML/JavaScript implementation that you can adapt for your project. You can find it [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/web/live_transcription.html), or load its content using `get_web_interface_html()` :
+The package includes an HTML/JavaScript implementation [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/web/live_transcription.html). You can also import it using `from whisperlivekit import get_web_interface_html` & `page = get_web_interface_html()`
 
-```python
-from whisperlivekit import get_web_interface_html
-html_content = get_web_interface_html()
-```
 
-## ⚙️ Configuration Reference
+### ⚙️ Parameters & Configuration
 
-WhisperLiveKit offers extensive configuration options:
+An important list of parameters can be changed. But what *should* you change?
+- the `--model` size. List and recommandations [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/available_models.md)
+- the `--language`.  List [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py)
+- the `--backend` ? you can switch to `--backend faster-whisper` if  `simulstreaming` does not work correctly or if you prefer to avoid the dual-license requirements.
+- `--warmup-file`, if you have one
+- `--host`, `--port`, `--ssl-certfile`, `--ssl-keyfile`, if you set up a server
+- `--diarization`, if you want to use it.
+
+The rest I don't recommend. But below are your options.
 
 | Parameter | Description | Default |
 |-----------|-------------|---------|
-| `--host` | Server host address | `localhost` |
-| `--port` | Server port | `8000` |
-| `--model` | Whisper model size. Caution : '.en' models do not work with Simulstreaming | `tiny` |
+| `--model` | Whisper model size. | `small` |
 | `--language` | Source language code or `auto` | `en` |
 | `--task` | `transcribe` or `translate` | `transcribe` |
-| `--backend` | Processing backend | `faster-whisper` |
-| `--diarization` | Enable speaker identification | `False` |
-| `--punctuation-split` | Use punctuation to improve speaker boundaries | `True` |
-| `--confidence-validation` | Use confidence scores for faster validation | `False` |
+| `--backend` | Processing backend | `simulstreaming` |
 | `--min-chunk-size` | Minimum audio chunk size (seconds) | `1.0` |
-| `--vac` | Use Voice Activity Controller | `False` |
+| `--no-vac` | Disable Voice Activity Controller | `False` |
 | `--no-vad` | Disable Voice Activity Detection | `False` |
-| `--buffer_trimming` | Buffer trimming strategy (`sentence` or `segment`) | `segment` |
 | `--warmup-file` | Audio file path for model warmup | `jfk.wav` |
+| `--host` | Server host address | `localhost` |
+| `--port` | Server port | `8000` |
 | `--ssl-certfile` | Path to the SSL certificate file (for HTTPS support) | `None` |
 | `--ssl-keyfile` | Path to the SSL private key file (for HTTPS support) | `None` |
-| `--segmentation-model` | Hugging Face model ID for pyannote.audio segmentation model. [Available models](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `pyannote/segmentation-3.0` |
-| `--embedding-model` | Hugging Face model ID for pyannote.audio embedding model. [Available models](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `speechbrain/spkrec-ecapa-voxceleb` |
 
-**SimulStreaming-specific Options:**
 
-| Parameter | Description | Default |
+| WhisperStreaming backend options | Description | Default |
+|-----------|-------------|---------|
+| `--confidence-validation` | Use confidence scores for faster validation | `False` |
+| `--buffer_trimming` | Buffer trimming strategy (`sentence` or `segment`) | `segment` |
+
+
+| SimulStreaming backend options | Description | Default |
 |-----------|-------------|---------|
 | `--frame-threshold` | AlignAtt frame threshold (lower = faster, higher = more accurate) | `25` |
 | `--beams` | Number of beams for beam search (1 = greedy decoding) | `1` |
@@ -216,69 +191,77 @@ WhisperLiveKit offers extensive configuration options:
 | `--static-init-prompt` | Static prompt that doesn't scroll | `None` |
 | `--max-context-tokens` | Maximum context tokens | `None` |
 | `--model-path` | Direct path to .pt model file. Download it if not found | `./base.pt` |
+| `--preloaded-model-count` | Optional. Number of models to preload in memory to speed up loading (set up to the expected number of concurrent users) | `1` |
 
-## 🔧 How It Works
+| Diarization options | Description | Default |
+|-----------|-------------|---------|
+| `--diarization` | Enable speaker identification | `False` |
+| `--diarization-backend` |  `diart` or `sortformer` | `sortformer` |
+| `--segmentation-model` | Hugging Face model ID for Diart segmentation model. [Available models](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `pyannote/segmentation-3.0` |
+| `--embedding-model` | Hugging Face model ID for Diart embedding model. [Available models](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `speechbrain/spkrec-ecapa-voxceleb` |
 
-1. **Audio Capture**: Browser's MediaRecorder API captures audio in webm/opus format
-2. **Streaming**: Audio chunks are sent to the server via WebSocket
-3. **Processing**: Server decodes audio with FFmpeg and streams into the model for transcription
-4. **Real-time Output**: Partial transcriptions appear immediately in light gray (the 'aperçu') and finalized text appears in normal color
-
-## 🚀 Deployment Guide
+### 🚀 Deployment Guide
 
 To deploy WhisperLiveKit in production:
-
-1. **Server Setup** (Backend):
+ 
+1. **Server Setup**: Install production ASGI server & launch with multiple workers
    ```bash
-   # Install production ASGI server
    pip install uvicorn gunicorn
-
-   # Launch with multiple workers
    gunicorn -k uvicorn.workers.UvicornWorker -w 4 your_app:app
    ```
 
-2. **Frontend Integration**:
-   - Host your customized version of the example HTML/JS in your web application
-   - Ensure WebSocket connection points to your server's address
+2. **Frontend**: Host your customized version of the `html` example & ensure WebSocket connection points correctly
 
 3. **Nginx Configuration** (recommended for production):
     ```nginx    
    server {
        listen 80;
        server_name your-domain.com;
-
-    location / {
-        proxy_pass http://localhost:8000;
-        proxy_set_header Upgrade $http_upgrade;
-        proxy_set_header Connection "upgrade";
-        proxy_set_header Host $host;
+        location / {
+            proxy_pass http://localhost:8000;
+            proxy_set_header Upgrade $http_upgrade;
+            proxy_set_header Connection "upgrade";
+            proxy_set_header Host $host;
     }}
     ```
 
 4. **HTTPS Support**: For secure deployments, use "wss://" instead of "ws://" in WebSocket URL
 
-### 🐋 Docker
+## 🐋 Docker
 
-A basic Dockerfile is provided which allows re-use of Python package installation options. ⚠️ For **large** models, ensure that your **docker runtime** has enough **memory** available. See below usage examples:
+Deploy the application easily using Docker with GPU or CPU support.
 
+### Prerequisites
+- Docker installed on your system
+- For GPU support: NVIDIA Docker runtime installed
 
-#### All defaults
-- Create a reusable image with only the basics and then run as a named container:
-    ```bash
-    docker build -t whisperlivekit-defaults .
-    docker create --gpus all --name whisperlivekit -p 8000:8000 whisperlivekit-defaults
-    docker start -i whisperlivekit
-    ```
+### Quick Start
+
+**With GPU acceleration (recommended):**
+```bash
+docker build -t wlk .
+docker run --gpus all -p 8000:8000 --name wlk wlk
+```
+
+**CPU only:**
+```bash
+docker build -f Dockerfile.cpu -t wlk .
+docker run -p 8000:8000 --name wlk wlk
+```
+
+### Advanced Usage
+
+**Custom configuration:**
+```bash
+# Example with custom model and language
+docker run --gpus all -p 8000:8000 --name wlk wlk --model large-v3 --language fr
+```
+
+### Memory Requirements
+- **Large models**: Ensure your Docker runtime has sufficient memory allocated
 
-    > **Note**: If you're running on a system without NVIDIA GPU support (such as Mac with Apple Silicon or any system without CUDA capabilities), you need to **remove the `--gpus all` flag** from the `docker create` command. Without GPU acceleration, transcription will use CPU only, which may be significantly slower. Consider using small models for better performance on CPU-only systems.
 
 #### Customization
-- Customize the container options:
-    ```bash
-    docker build -t whisperlivekit-defaults .
-    docker create --gpus all --name whisperlivekit-base -p 8000:8000 whisperlivekit-defaults --model base
-    docker start -i whisperlivekit-base
-    ```
 
 - `--build-arg` Options:
   - `EXTRAS="whisper-timestamped"` - Add extras to the image's installation (no spaces). Remember to set necessary container options!
@@ -287,10 +270,3 @@ A basic Dockerfile is provided which allows re-use of Python package installatio
 
 ## 🔮 Use Cases
 Capture discussions in real-time for meeting transcription, help hearing-impaired users follow conversations through accessibility tools, transcribe podcasts or videos automatically for content creation, transcribe support calls with speaker identification for customer service...
-
-## 🙏 Acknowledgments
-
-We extend our gratitude to the original authors of:
-
-| [Whisper Streaming](https://github.com/ufal/whisper_streaming)  | [SimulStreaming](https://github.com/ufal/SimulStreaming) | [Diart](https://github.com/juanmc2005/diart) | [OpenAI Whisper](https://github.com/openai/whisper) |
-| -------- | ------- | -------- | ------- |

available_models.md

@@ -0,0 +1,72 @@
+# Available model sizes:
+
+- tiny.en (english only)
+- tiny
+- base.en (english only)
+- base
+- small.en (english only)
+- small
+- medium.en (english only)
+- medium
+- large-v1
+- large-v2
+- large-v3
+- large-v3-turbo
+
+## How to choose?
+
+### Language Support
+- **English only**: Use `.en` models for better accuracy and faster processing when you only need English transcription
+- **Multilingual**: Do not use `.en` models.
+
+### Resource Constraints
+- **Limited GPU/CPU or need for very low latency**: Choose `small` or smaller models
+  - `tiny`: Fastest, lowest resource usage, acceptable quality for simple audio
+  - `base`: Good balance of speed and accuracy for basic use cases
+  - `small`: Better accuracy while still being resource-efficient
+- **Good resources available**: Use `large` models for best accuracy
+  - `large-v2`: Excellent accuracy, good multilingual support
+  - `large-v3`: Best overall accuracy and language support
+
+### Special Cases
+- **No translation needed**: Use `large-v3-turbo`
+  - Same transcription quality as `large-v2` but significantly faster
+  - **Important**: Does not translate correctly, only transcribes
+
+### Model Comparison Table
+
+| Model | Speed | Accuracy | Multilingual | Translation | Best Use Case |
+|-------|--------|----------|--------------|-------------|---------------|
+| tiny(.en) | Fastest | Basic | Yes/No | Yes/No | Real-time, low resources |
+| base(.en) | Fast | Good | Yes/No | Yes/No | Balanced performance |
+| small(.en) | Medium | Better | Yes/No | Yes/No | Quality on limited hardware |
+| medium(.en) | Slow | High | Yes/No | Yes/No | High quality, moderate resources |
+| large-v2 | Slowest | Excellent | Yes | Yes | Best overall quality |
+| large-v3 | Slowest | Excellent | Yes | Yes | Maximum accuracy |
+| large-v3-turbo | Fast | Excellent | Yes | No | Fast, high-quality transcription |
+
+### Additional Considerations
+
+**Model Performance**:
+- Accuracy improves significantly from tiny to large models
+- English-only models are ~10-15% more accurate for English audio
+- Newer versions (v2, v3) have better punctuation and formatting
+
+**Hardware Requirements**:
+- `tiny`: ~1GB VRAM
+- `base`: ~1GB VRAM  
+- `small`: ~2GB VRAM
+- `medium`: ~5GB VRAM
+- `large`: ~10GB VRAM
+
+**Audio Quality Impact**:
+- Clean, clear audio: smaller models may suffice
+- Noisy, accented, or technical audio: larger models recommended
+- Phone/low-quality audio: use at least `small` model
+
+### Quick Decision Tree
+1. English only? → Add `.en` to your choice
+2. Limited resources or need speed? → `small` or smaller
+3. Good hardware and want best quality? → `large-v3`
+4. Need fast, high-quality transcription without translation? → `large-v3-turbo`
+5. Need translation capabilities? → `large-v2` or `large-v3` (avoid turbo)

pyproject.toml

@@ -0,0 +1,51 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "whisperlivekit"
+version = "0.2.7"
+description = "Real-time, Fully Local Whisper's Speech-to-Text and Speaker Diarization"
+readme = "README.md"
+authors = [
+    { name = "Quentin Fuxa" }
+]
+license = { file = "LICENSE" }
+requires-python = ">=3.9"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Multimedia :: Sound/Audio :: Speech"
+]
+dependencies = [
+    "fastapi",
+    "librosa",
+    "soundfile",
+    "faster-whisper",
+    "uvicorn",
+    "websockets",
+    "torch",
+    "tqdm",
+    "tiktoken",
+    'triton>=2.0.0,<3; platform_machine == "x86_64" and (sys_platform == "linux" or sys_platform == "linux2")'
+]
+
+[project.optional-dependencies]
+sentence = ["mosestokenizer", "wtpsplit"]
+
+[project.urls]
+Homepage = "https://github.com/QuentinFuxa/WhisperLiveKit"
+
+[project.scripts]
+whisperlivekit-server = "whisperlivekit.basic_server:main"
+
+[tool.setuptools]
+packages = ["whisperlivekit", "whisperlivekit.diarization", "whisperlivekit.simul_whisper", "whisperlivekit.simul_whisper.whisper", "whisperlivekit.simul_whisper.whisper.assets", "whisperlivekit.simul_whisper.whisper.normalizers", "whisperlivekit.web", "whisperlivekit.whisper_streaming_custom"]
+
+[tool.setuptools.package-data]
+whisperlivekit = ["web/*.html", "web/*.css", "web/*.js", "web/src/*.svg"]
+"whisperlivekit.simul_whisper.whisper.assets" = ["*.tiktoken", "*.npz"]

setup.py

@@ -1,54 +0,0 @@
-from setuptools import setup, find_packages
-setup(
-    name="whisperlivekit",
-    version="0.2.4.dev0",
-    description="Real-time, Fully Local Whisper's Speech-to-Text and Speaker Diarization",
-    long_description=open("README.md", "r", encoding="utf-8").read(),
-    long_description_content_type="text/markdown",
-    author="Quentin Fuxa",
-    url="https://github.com/QuentinFuxa/WhisperLiveKit",
-    packages=find_packages(),
-    install_requires=[
-        "fastapi",
-        "librosa",
-        "soundfile",
-        "faster-whisper",
-        "uvicorn",
-        "websockets",
-    ],
-    extras_require={
-        "diarization": ["diart"],
-        "vac": ["torch"],
-        "sentence": ["mosestokenizer", "wtpsplit"],
-        "whisper": ["whisper"],
-        "whisper-timestamped": ["whisper-timestamped"],
-        "mlx-whisper": ["mlx-whisper"],
-        "openai": ["openai"],
-        "simulstreaming": [
-            "torch",
-            "tqdm",
-            "tiktoken",
-            "numpy<2.0.0",
-            "triton>=2.0.0,<3;platform_machine==\"x86_64\" and sys_platform==\"linux\" or sys_platform==\"linux2\"",
-        ],
-    },
-    package_data={
-        'whisperlivekit': ['web/*.html'],
-        'whisperlivekit.simul_whisper.whisper.assets': ['*.tiktoken', '*.npz'],
-    },
-    entry_points={
-        'console_scripts': [
-            'whisperlivekit-server=whisperlivekit.basic_server:main',
-        ],
-    },
-    classifiers=[
-        "Development Status :: 4 - Beta",
-        "Intended Audience :: Developers",
-        "License :: OSI Approved :: MIT License",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        "Topic :: Multimedia :: Sound/Audio :: Speech",
-    ],
-    python_requires=">=3.9",
-)

whisperlivekit/__init__.py

@@ -1,4 +1,3 @@
-from .download_simulstreaming_backend import download_simulstreaming_backend
 from .audio_processor import AudioProcessor
 from .core import TranscriptionEngine
 from .parse_args import parse_args

whisperlivekit/audio_processor.py

@@ -4,12 +4,11 @@ from time import time, sleep
 import math
 import logging
 import traceback
-from datetime import timedelta
-from whisperlivekit.timed_objects import ASRToken
-from whisperlivekit.whisper_streaming_custom.whisper_online import online_factory
-from whisperlivekit.core import TranscriptionEngine
+from whisperlivekit.timed_objects import ASRToken, Silence
+from whisperlivekit.core import TranscriptionEngine, online_factory, online_diarization_factory
 from whisperlivekit.ffmpeg_manager import FFmpegManager, FFmpegState
-
+from whisperlivekit.silero_vad_iterator import FixedVADIterator
+from whisperlivekit.results_formater import format_output, format_time
 # Set up logging once
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
@@ -17,10 +16,6 @@ logger.setLevel(logging.DEBUG)
 
 SENTINEL = object() # unique sentinel object for end of stream marker
 
-def format_time(seconds: float) -> str:
-    """Format seconds as HH:MM:SS."""
-    return str(timedelta(seconds=int(seconds)))
-
 class AudioProcessor:
     """
     Processes audio streams for transcription and diarization.
@@ -46,25 +41,31 @@ class AudioProcessor:
         self.last_ffmpeg_activity = time()
         self.ffmpeg_health_check_interval = 5
         self.ffmpeg_max_idle_time = 10
+        self.debug = False
 
         # State management
         self.is_stopping = False
+        self.silence = False
+        self.silence_duration = 0.0
         self.tokens = []
         self.buffer_transcription = ""
         self.buffer_diarization = ""
-        self.full_transcription = ""
         self.end_buffer = 0
         self.end_attributed_speaker = 0
         self.lock = asyncio.Lock()
-        self.beg_loop = time()
+        self.beg_loop = None #to deal with a potential little lag at the websocket initialization, this is now set in process_audio
         self.sep = " "  # Default separator
         self.last_response_content = ""
         
         # Models and processing
         self.asr = models.asr
         self.tokenizer = models.tokenizer
-        self.diarization = models.diarization
-        
+        self.vac_model = models.vac_model
+        if self.args.vac:
+            self.vac = FixedVADIterator(models.vac_model)
+        else:
+            self.vac = None
+            
         self.ffmpeg_manager = FFmpegManager(
             sample_rate=self.sample_rate,
             channels=self.channels
@@ -91,18 +92,22 @@ class AudioProcessor:
         # Initialize transcription engine if enabled
         if self.args.transcription:
             self.online = online_factory(self.args, models.asr, models.tokenizer)
+            
+        # Initialize diarization engine if enabled
+        if self.args.diarization:
+            self.diarization = online_diarization_factory(self.args, models.diarization_model)
+
 
     def convert_pcm_to_float(self, pcm_buffer):
         """Convert PCM buffer in s16le format to normalized NumPy array."""
         return np.frombuffer(pcm_buffer, dtype=np.int16).astype(np.float32) / 32768.0
 
-    async def update_transcription(self, new_tokens, buffer, end_buffer, full_transcription, sep):
+    async def update_transcription(self, new_tokens, buffer, end_buffer, sep):
         """Thread-safe update of transcription with new data."""
         async with self.lock:
             self.tokens.extend(new_tokens)
             self.buffer_transcription = buffer
             self.end_buffer = end_buffer
-            self.full_transcription = full_transcription
             self.sep = sep
             
     async def update_diarization(self, end_attributed_speaker, buffer_diarization=""):
@@ -129,12 +134,12 @@ class AudioProcessor:
             # Calculate remaining times
             remaining_transcription = 0
             if self.end_buffer > 0:
-                remaining_transcription = max(0, round(current_time - self.beg_loop - self.end_buffer, 2))
+                remaining_transcription = max(0, round(current_time - self.beg_loop - self.end_buffer, 1))
                 
             remaining_diarization = 0
             if self.tokens:
                 latest_end = max(self.end_buffer, self.tokens[-1].end if self.tokens else 0)
-                remaining_diarization = max(0, round(latest_end - self.end_attributed_speaker, 2))
+                remaining_diarization = max(0, round(latest_end - self.end_attributed_speaker, 1))
                 
             return {
                 "tokens": self.tokens.copy(),
@@ -153,7 +158,6 @@ class AudioProcessor:
             self.tokens = []
             self.buffer_transcription = self.buffer_diarization = ""
             self.end_buffer = self.end_attributed_speaker = 0
-            self.full_transcription = self.last_response_content = ""
             self.beg_loop = time()
 
     async def ffmpeg_stdout_reader(self):
@@ -205,18 +209,44 @@ class AudioProcessor:
                     pcm_array = self.convert_pcm_to_float(self.pcm_buffer[:self.max_bytes_per_sec])
                     self.pcm_buffer = self.pcm_buffer[self.max_bytes_per_sec:]
                     
-                    # Send to transcription if enabled
-                    if self.args.transcription and self.transcription_queue:
-                        await self.transcription_queue.put(pcm_array.copy())
+                    res = None
+                    end_of_audio = False
+                    silence_buffer = None
+                    
+                    if self.args.vac:
+                        res = self.vac(pcm_array)
+                    
+                    if res is not None:
+                        if res.get('end', 0) > res.get('start', 0):
+                            end_of_audio = True
+                        elif self.silence: #end of silence
+                            self.silence = False
+                            silence_buffer = Silence(duration=time() - self.start_silence)
+                            
+                    if silence_buffer:
+                        if self.args.transcription and self.transcription_queue:
+                            await self.transcription_queue.put(silence_buffer)
+                        if self.args.diarization and self.diarization_queue:
+                            await self.diarization_queue.put(silence_buffer)
 
-                    # Send to diarization if enabled
-                    if self.args.diarization and self.diarization_queue:
-                        await self.diarization_queue.put(pcm_array.copy())
+                    if not self.silence:                            
+                        if self.args.transcription and self.transcription_queue:
+                            await self.transcription_queue.put(pcm_array.copy())
+
+                        if self.args.diarization and self.diarization_queue:
+                            await self.diarization_queue.put(pcm_array.copy())
+                        
+                        self.silence_duration = 0.0
+                        if end_of_audio:
+                            self.silence = True
+                            self.start_silence = time()
 
                     # Sleep if no processing is happening
                     if not self.args.transcription and not self.args.diarization:
                         await asyncio.sleep(0.1)
                     
+                    
+                    
             except Exception as e:
                 logger.warning(f"Exception in ffmpeg_stdout_reader: {e}")
                 logger.warning(f"Traceback: {traceback.format_exc()}")
@@ -238,36 +268,48 @@ class AudioProcessor:
 
     async def transcription_processor(self):
         """Process audio chunks for transcription."""
-        self.full_transcription = ""
         self.sep = self.online.asr.sep
         cumulative_pcm_duration_stream_time = 0.0
         
         while True:
             try:
-                pcm_array = await self.transcription_queue.get()
-                if pcm_array is SENTINEL:
+                item = await self.transcription_queue.get()
+                if item is SENTINEL:
                     logger.debug("Transcription processor received sentinel. Finishing.")
                     self.transcription_queue.task_done()
                     break
                 
-                if not self.online: # Should not happen if queue is used
+                if not self.online:
                     logger.warning("Transcription processor: self.online not initialized.")
                     self.transcription_queue.task_done()
                     continue
 
                 asr_internal_buffer_duration_s = len(getattr(self.online, 'audio_buffer', [])) / self.online.SAMPLING_RATE
                 transcription_lag_s = max(0.0, time() - self.beg_loop - self.end_buffer)
-
-                logger.info(
-                    f"ASR processing: internal_buffer={asr_internal_buffer_duration_s:.2f}s, "
-                    f"lag={transcription_lag_s:.2f}s."
-                )
+                asr_processing_logs = f"internal_buffer={asr_internal_buffer_duration_s:.2f}s | lag={transcription_lag_s:.2f}s |"
+                if type(item) is Silence:
+                    asr_processing_logs += f" + Silence of = {item.duration:.2f}s"
+                    if self.tokens:
+                        asr_processing_logs += f" | last_end = {self.tokens[-1].end} |"
+                logger.info(asr_processing_logs)
                 
-                # Process transcription
-                duration_this_chunk = len(pcm_array) / self.sample_rate if isinstance(pcm_array, np.ndarray) else 0
+                if type(item) is Silence:
+                    cumulative_pcm_duration_stream_time += item.duration
+                    self.online.insert_silence(item.duration, self.tokens[-1].end)
+                    continue
+                
+                if isinstance(item, np.ndarray):
+                    pcm_array = item
+                else:
+                    raise Exception('item should be pcm_array')
+                
+                duration_this_chunk = len(pcm_array) / self.sample_rate
                 cumulative_pcm_duration_stream_time += duration_this_chunk
                 stream_time_end_of_current_pcm = cumulative_pcm_duration_stream_time
 
+                
+                    
+
                 self.online.insert_audio_chunk(pcm_array, stream_time_end_of_current_pcm)
                 new_tokens, current_audio_processed_upto = self.online.process_iter()
                 
@@ -277,8 +319,6 @@ class AudioProcessor:
 
                 if new_tokens:
                     validated_text = self.sep.join([t.text for t in new_tokens])
-                    self.full_transcription += validated_text
-                    
                     if buffer_text.startswith(validated_text):
                         buffer_text = buffer_text[len(validated_text):].lstrip()
 
@@ -295,7 +335,7 @@ class AudioProcessor:
                 new_end_buffer = max(candidate_end_times)
                 
                 await self.update_transcription(
-                    new_tokens, buffer_text, new_end_buffer, self.full_transcription, self.sep
+                    new_tokens, buffer_text, new_end_buffer, self.sep
                 )
                 self.transcription_queue.task_done()
                 
@@ -310,15 +350,25 @@ class AudioProcessor:
     async def diarization_processor(self, diarization_obj):
         """Process audio chunks for speaker diarization."""
         buffer_diarization = ""
-        
+        cumulative_pcm_duration_stream_time = 0.0
         while True:
             try:
-                pcm_array = await self.diarization_queue.get()
-                if pcm_array is SENTINEL:
+                item = await self.diarization_queue.get()
+                if item is SENTINEL:
                     logger.debug("Diarization processor received sentinel. Finishing.")
                     self.diarization_queue.task_done()
                     break
                 
+                if type(item) is Silence:
+                    cumulative_pcm_duration_stream_time += item.duration
+                    diarization_obj.insert_silence(item.duration)
+                    continue
+    
+                if isinstance(item, np.ndarray):
+                    pcm_array = item
+                else:
+                    raise Exception('item should be pcm_array') 
+                
                 # Process diarization
                 await diarization_obj.diarize(pcm_array)
                 
@@ -344,6 +394,8 @@ class AudioProcessor:
 
     async def results_formatter(self):
         """Format processing results for output."""
+        last_sent_trans = None
+        last_sent_diar = None
         while True:
             try:
                 ffmpeg_state = await self.ffmpeg_manager.get_state()
@@ -368,7 +420,7 @@ class AudioProcessor:
                 buffer_diarization = state["buffer_diarization"]
                 end_attributed_speaker = state["end_attributed_speaker"]
                 sep = state["sep"]
-                
+                                
                 # Add dummy tokens if needed
                 if (not tokens or tokens[-1].is_dummy) and not self.args.transcription and self.args.diarization:
                     await self.add_dummy_token()
@@ -377,40 +429,13 @@ class AudioProcessor:
                     tokens = state["tokens"]
                 
                 # Format output
-                previous_speaker = -1
-                lines = []
-                last_end_diarized = 0
-                undiarized_text = []
-                
-                # Process each token
-                for token in tokens:
-                    speaker = token.speaker
-                    
-                    # Handle diarization
-                    if self.args.diarization:
-                        if (speaker in [-1, 0]) and token.end >= end_attributed_speaker:
-                            undiarized_text.append(token.text)
-                            continue
-                        elif (speaker in [-1, 0]) and token.end < end_attributed_speaker:
-                            speaker = previous_speaker
-                        if speaker not in [-1, 0]:
-                            last_end_diarized = max(token.end, last_end_diarized)
-
-                    # Group by speaker
-                    if speaker != previous_speaker or not lines:
-                        lines.append({
-                            "speaker": speaker,
-                            "text": token.text,
-                            "beg": format_time(token.start),
-                            "end": format_time(token.end),
-                            "diff": round(token.end - last_end_diarized, 2)
-                        })
-                        previous_speaker = speaker
-                    elif token.text:  # Only append if text isn't empty
-                        lines[-1]["text"] += sep + token.text
-                        lines[-1]["end"] = format_time(token.end)
-                        lines[-1]["diff"] = round(token.end - last_end_diarized, 2)
-                
+                lines, undiarized_text, buffer_transcription, buffer_diarization = format_output(
+                    state,
+                    self.silence,
+                    current_time = time() - self.beg_loop if self.beg_loop else None,
+                    diarization = self.args.diarization,
+                    debug = self.debug
+                )
                 # Handle undiarized text
                 if undiarized_text:
                     combined = sep.join(undiarized_text)
@@ -440,17 +465,26 @@ class AudioProcessor:
                     "buffer_transcription": buffer_transcription,
                     "buffer_diarization": buffer_diarization,
                     "remaining_time_transcription": state["remaining_time_transcription"],
-                    "remaining_time_diarization": state["remaining_time_diarization"]
+                    "remaining_time_diarization": state["remaining_time_diarization"] if self.args.diarization else 0
                 }
                 
                 current_response_signature = f"{response_status} | " + \
                                            ' '.join([f"{line['speaker']} {line['text']}" for line in final_lines_for_response]) + \
                                            f" | {buffer_transcription} | {buffer_diarization}"
                 
-                if current_response_signature != self.last_response_content and \
-                   (final_lines_for_response or buffer_transcription or buffer_diarization or response_status == "no_audio_detected"):
+                trans = state["remaining_time_transcription"]
+                diar = state["remaining_time_diarization"]
+                should_push = (
+                    current_response_signature != self.last_response_content
+                    or last_sent_trans is None
+                    or round(trans, 1) != round(last_sent_trans, 1)
+                    or round(diar, 1) != round(last_sent_diar, 1)
+                )
+                if should_push and (final_lines_for_response or buffer_transcription or buffer_diarization or response_status == "no_audio_detected" or trans > 0 or diar > 0):
                     yield response
                     self.last_response_content = current_response_signature
+                    last_sent_trans = trans
+                    last_sent_diar = diar
                 
                 # Check for termination condition
                 if self.is_stopping:
@@ -562,6 +596,10 @@ class AudioProcessor:
 
     async def process_audio(self, message):
         """Process incoming audio data."""
+
+        if not self.beg_loop:
+            self.beg_loop = time()
+
         if not message:
             logger.info("Empty audio message received, initiating stop sequence.")
             self.is_stopping = True

whisperlivekit/basic_server.py

@@ -5,6 +5,9 @@ from fastapi.middleware.cors import CORSMiddleware
 from whisperlivekit import TranscriptionEngine, AudioProcessor, get_web_interface_html, parse_args
 import asyncio
 import logging
+from starlette.staticfiles import StaticFiles
+import pathlib
+import whisperlivekit.web as webpkg
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logging.getLogger().setLevel(logging.WARNING)
@@ -30,6 +33,8 @@ app.add_middleware(
     allow_methods=["*"],
     allow_headers=["*"],
 )
+web_dir = pathlib.Path(webpkg.__file__).parent
+app.mount("/web", StaticFiles(directory=str(web_dir)), name="web")
 
 @app.get("/")
 async def get():
@@ -47,7 +52,7 @@ async def handle_websocket_results(websocket, results_generator):
     except WebSocketDisconnect:
         logger.info("WebSocket disconnected while handling results (client likely closed connection).")
     except Exception as e:
-        logger.warning(f"Error in WebSocket results handler: {e}")
+        logger.exception(f"Error in WebSocket results handler: {e}")
 
 
 @app.websocket("/asr")

whisperlivekit/core.py

@@ -1,9 +1,12 @@
 try:
-    from whisperlivekit.whisper_streaming_custom.whisper_online import backend_factory, warmup_asr
+    from whisperlivekit.whisper_streaming_custom.whisper_online import backend_factory
+    from whisperlivekit.whisper_streaming_custom.online_asr import OnlineASRProcessor
 except ImportError:
-    from .whisper_streaming_custom.whisper_online import backend_factory, warmup_asr
+    from .whisper_streaming_custom.whisper_online import backend_factory
+    from .whisper_streaming_custom.online_asr import OnlineASRProcessor
+from whisperlivekit.warmup import warmup_asr, warmup_online
 from argparse import Namespace
-
+import sys
 
 class TranscriptionEngine:
     _instance = None
@@ -22,7 +25,6 @@ class TranscriptionEngine:
             "host": "localhost",
             "port": 8000,
             "warmup_file": None,
-            "confidence_validation": False,
             "diarization": False,
             "punctuation_split": False,
             "min_chunk_size": 0.5,
@@ -32,22 +34,22 @@ class TranscriptionEngine:
             "lan": "auto",
             "task": "transcribe",
             "backend": "faster-whisper",
-            "vac": False,
+            "vac": True,
             "vac_chunk_size": 0.04,
-            "buffer_trimming": "segment",
-            "buffer_trimming_sec": 15,
             "log_level": "DEBUG",
             "ssl_certfile": None,
             "ssl_keyfile": None,
             "transcription": True,
             "vad": True,
-            "segmentation_model": "pyannote/segmentation-3.0",
-            "embedding_model": "pyannote/embedding",
+            # whisperstreaming params:
+            "buffer_trimming": "segment",
+            "confidence_validation": False,
+            "buffer_trimming_sec": 15,
             # simulstreaming params:
             "frame_threshold": 25,
             "beams": 1,
             "decoder_type": None,
-            "audio_max_len": 30.0,
+            "audio_max_len": 20.0,
             "audio_min_len": 0.0,
             "cif_ckpt_path": None,
             "never_fire": False,
@@ -55,6 +57,10 @@ class TranscriptionEngine:
             "static_init_prompt": None,
             "max_context_tokens": None,
             "model_path": './base.pt',
+            "diarization_backend": "sortformer",
+            # diart params:
+            "segmentation_model": "pyannote/segmentation-3.0",
+            "embedding_model": "pyannote/embedding",
         }
 
         config_dict = {**defaults, **kwargs}
@@ -63,6 +69,8 @@ class TranscriptionEngine:
             config_dict['transcription'] = not kwargs['no_transcription']
         if 'no_vad' in kwargs:
             config_dict['vad'] = not kwargs['no_vad']
+        if 'no_vac' in kwargs:
+            config_dict['vac'] = not kwargs['no_vac']
         
         config_dict.pop('no_transcription', None)
         config_dict.pop('no_vad', None)
@@ -76,17 +84,85 @@ class TranscriptionEngine:
         self.asr = None
         self.tokenizer = None
         self.diarization = None
+        self.vac_model = None
+        
+        if self.args.vac:
+            import torch
+            self.vac_model, _ = torch.hub.load(repo_or_dir="snakers4/silero-vad", model="silero_vad")            
         
         if self.args.transcription:
-            self.asr, self.tokenizer = backend_factory(self.args)
-            warmup_asr(self.asr, self.args.warmup_file)
+            if self.args.backend == "simulstreaming": 
+                from whisperlivekit.simul_whisper import SimulStreamingASR
+                self.tokenizer = None
+                simulstreaming_kwargs = {}
+                for attr in ['frame_threshold', 'beams', 'decoder_type', 'audio_max_len', 'audio_min_len', 
+                            'cif_ckpt_path', 'never_fire', 'init_prompt', 'static_init_prompt', 
+                            'max_context_tokens', 'model_path', 'warmup_file', 'preload_model_count']:
+                    if hasattr(self.args, attr):
+                        simulstreaming_kwargs[attr] = getattr(self.args, attr)
+        
+                # Add segment_length from min_chunk_size
+                simulstreaming_kwargs['segment_length'] = getattr(self.args, 'min_chunk_size', 0.5)
+                simulstreaming_kwargs['task'] = self.args.task
+                
+                size = self.args.model
+                self.asr = SimulStreamingASR(
+                    modelsize=size,
+                    lan=self.args.lan,
+                    cache_dir=getattr(self.args, 'model_cache_dir', None),
+                    model_dir=getattr(self.args, 'model_dir', None),
+                    **simulstreaming_kwargs
+                )
+
+            else:
+                self.asr, self.tokenizer = backend_factory(self.args)
+            warmup_asr(self.asr, self.args.warmup_file) #for simulstreaming, warmup should be done in the online class not here
 
         if self.args.diarization:
-            from whisperlivekit.diarization.diarization_online import DiartDiarization
-            self.diarization = DiartDiarization(
-                block_duration=self.args.min_chunk_size,
-                segmentation_model_name=self.args.segmentation_model,
-                embedding_model_name=self.args.embedding_model
-            )
+            if self.args.diarization_backend == "diart":
+                from whisperlivekit.diarization.diart_backend import DiartDiarization
+                self.diarization_model = DiartDiarization(
+                    block_duration=self.args.min_chunk_size,
+                    segmentation_model_name=self.args.segmentation_model,
+                    embedding_model_name=self.args.embedding_model
+                )
+            elif self.args.diarization_backend == "sortformer":
+                from whisperlivekit.diarization.sortformer_backend import SortformerDiarization
+                self.diarization_model = SortformerDiarization()
+            else:
+                raise ValueError(f"Unknown diarization backend: {self.args.diarization_backend}")
             
         TranscriptionEngine._initialized = True
+
+
+
+def online_factory(args, asr, tokenizer, logfile=sys.stderr):
+    if args.backend == "simulstreaming":    
+        from whisperlivekit.simul_whisper import SimulStreamingOnlineProcessor
+        online = SimulStreamingOnlineProcessor(
+            asr,
+            logfile=logfile,
+        )
+        # warmup_online(online, args.warmup_file)
+    else:
+        online = OnlineASRProcessor(
+            asr,
+            tokenizer,
+            logfile=logfile,
+            buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec),
+            confidence_validation = args.confidence_validation
+        )
+    return online
+  
+  
+def online_diarization_factory(args, diarization_backend):
+    if args.diarization_backend == "diart":
+        online = diarization_backend
+        # Not the best here, since several user/instances will share the same backend, but diart is not SOTA anymore and sortformer is recommanded
+    
+    if args.diarization_backend == "sortformer":
+        from whisperlivekit.diarization.sortformer_backend import SortformerDiarizationOnline
+        online = SortformerDiarizationOnline(shared_model=diarization_backend)
+    return online
+
+        

whisperlivekit/diarization/diart_backend.py

@@ -29,6 +29,7 @@ class DiarizationObserver(Observer):
         self.speaker_segments = []
         self.processed_time = 0
         self.segment_lock = threading.Lock()
+        self.global_time_offset = 0.0
     
     def on_next(self, value: Tuple[Annotation, Any]):
         annotation, audio = value
@@ -49,8 +50,8 @@ class DiarizationObserver(Observer):
                         print(f"  {speaker}: {start:.2f}s-{end:.2f}s")
                         self.speaker_segments.append(SpeakerSegment(
                             speaker=speaker,
-                            start=start,
-                            end=end
+                            start=start + self.global_time_offset,
+                            end=end + self.global_time_offset
                         ))
             else:
                 logger.debug("\nNo speakers detected in this segment")
@@ -199,6 +200,9 @@ class DiartDiarization:
         self.inference.attach_observers(self.observer)
         asyncio.get_event_loop().run_in_executor(None, self.inference)
 
+    def insert_silence(self, silence_duration):
+        self.observer.global_time_offset += silence_duration
+
     async def diarize(self, pcm_array: np.ndarray):
         """
         Process audio data for diarization.

whisperlivekit/diarization/sortformer_backend.py

@@ -0,0 +1,457 @@
+import numpy as np
+import torch
+import logging
+import threading
+import time
+import wave
+from typing import List, Optional
+from queue import SimpleQueue, Empty
+
+from whisperlivekit.timed_objects import SpeakerSegment
+
+logger = logging.getLogger(__name__)
+
+try:
+    from nemo.collections.asr.models import SortformerEncLabelModel
+    from nemo.collections.asr.modules import AudioToMelSpectrogramPreprocessor
+except ImportError:
+    raise SystemExit("""Please use `pip install "git+https://github.com/NVIDIA/NeMo.git@main#egg=nemo_toolkit[asr]"` to use the Sortformer diarization""")
+
+
+class StreamingSortformerState:
+    """
+    This class creates a class instance that will be used to store the state of the
+    streaming Sortformer model.
+
+    Attributes:
+        spkcache (torch.Tensor): Speaker cache to store embeddings from start
+        spkcache_lengths (torch.Tensor): Lengths of the speaker cache
+        spkcache_preds (torch.Tensor): The speaker predictions for the speaker cache parts
+        fifo (torch.Tensor): FIFO queue to save the embedding from the latest chunks
+        fifo_lengths (torch.Tensor): Lengths of the FIFO queue
+        fifo_preds (torch.Tensor): The speaker predictions for the FIFO queue parts
+        spk_perm (torch.Tensor): Speaker permutation information for the speaker cache
+        mean_sil_emb (torch.Tensor): Mean silence embedding
+        n_sil_frames (torch.Tensor): Number of silence frames
+    """
+
+    def __init__(self):
+        self.spkcache = None  # Speaker cache to store embeddings from start
+        self.spkcache_lengths = None
+        self.spkcache_preds = None  # speaker cache predictions
+        self.fifo = None  # to save the embedding from the latest chunks
+        self.fifo_lengths = None
+        self.fifo_preds = None
+        self.spk_perm = None
+        self.mean_sil_emb = None
+        self.n_sil_frames = None
+
+
+class SortformerDiarization:
+    def __init__(self, model_name: str = "nvidia/diar_streaming_sortformer_4spk-v2"):
+        """
+        Stores the shared streaming Sortformer diarization model. Used when a new online_diarization is initialized.
+        """
+        self._load_model(model_name)
+    
+    def _load_model(self, model_name: str):
+        """Load and configure the Sortformer model for streaming."""
+        try:
+            self.diar_model = SortformerEncLabelModel.from_pretrained(model_name)
+            self.diar_model.eval()
+
+            if torch.cuda.is_available():
+                self.diar_model.to(torch.device("cuda"))
+                logger.info("Using CUDA for Sortformer model")
+            else:
+                logger.info("Using CPU for Sortformer model")
+
+            self.diar_model.sortformer_modules.chunk_len = 10
+            self.diar_model.sortformer_modules.subsampling_factor = 10
+            self.diar_model.sortformer_modules.chunk_right_context = 0
+            self.diar_model.sortformer_modules.chunk_left_context = 10
+            self.diar_model.sortformer_modules.spkcache_len = 188
+            self.diar_model.sortformer_modules.fifo_len = 188
+            self.diar_model.sortformer_modules.spkcache_update_period = 144
+            self.diar_model.sortformer_modules.log = False
+            self.diar_model.sortformer_modules._check_streaming_parameters()
+                        
+        except Exception as e:
+            logger.error(f"Failed to load Sortformer model: {e}")
+            raise
+ 
+class SortformerDiarizationOnline:
+    def __init__(self, shared_model, sample_rate: int = 16000):
+        """
+        Initialize the streaming Sortformer diarization system.
+        
+        Args:
+            sample_rate: Audio sample rate (default: 16000)
+            model_name: Pre-trained model name (default: "nvidia/diar_streaming_sortformer_4spk-v2")
+        """
+        self.sample_rate = sample_rate
+        self.speaker_segments = []
+        self.buffer_audio = np.array([], dtype=np.float32)
+        self.segment_lock = threading.Lock()
+        self.global_time_offset = 0.0
+        self.processed_time = 0.0
+        self.debug = False
+                
+        self.diar_model = shared_model.diar_model
+             
+        self.audio2mel = AudioToMelSpectrogramPreprocessor(
+            window_size=0.025,
+            normalize="NA",
+            n_fft=512,
+            features=128,
+            pad_to=0
+        )
+        
+        self.chunk_duration_seconds = (
+            self.diar_model.sortformer_modules.chunk_len * 
+            self.diar_model.sortformer_modules.subsampling_factor * 
+            self.diar_model.preprocessor._cfg.window_stride
+        )
+        
+        self._init_streaming_state()
+        
+        self._previous_chunk_features = None
+        self._chunk_index = 0
+        self._len_prediction = None
+        
+        # Audio buffer to store PCM chunks for debugging
+        self.audio_buffer = []
+        
+        # Buffer for accumulating audio chunks until reaching chunk_duration_seconds
+        self.audio_chunk_buffer = []
+        self.accumulated_duration = 0.0
+        
+        logger.info("SortformerDiarization initialized successfully")
+
+
+    def _init_streaming_state(self):
+        """Initialize the streaming state for the model."""
+        batch_size = 1
+        device = self.diar_model.device
+        
+        self.streaming_state = StreamingSortformerState()
+        self.streaming_state.spkcache = torch.zeros(
+            (batch_size, self.diar_model.sortformer_modules.spkcache_len, self.diar_model.sortformer_modules.fc_d_model), 
+            device=device
+        )
+        self.streaming_state.spkcache_preds = torch.zeros(
+            (batch_size, self.diar_model.sortformer_modules.spkcache_len, self.diar_model.sortformer_modules.n_spk), 
+            device=device
+        )
+        self.streaming_state.spkcache_lengths = torch.zeros((batch_size,), dtype=torch.long, device=device)
+        self.streaming_state.fifo = torch.zeros(
+            (batch_size, self.diar_model.sortformer_modules.fifo_len, self.diar_model.sortformer_modules.fc_d_model), 
+            device=device
+        )
+        self.streaming_state.fifo_lengths = torch.zeros((batch_size,), dtype=torch.long, device=device)
+        self.streaming_state.mean_sil_emb = torch.zeros((batch_size, self.diar_model.sortformer_modules.fc_d_model), device=device)
+        self.streaming_state.n_sil_frames = torch.zeros((batch_size,), dtype=torch.long, device=device)
+        
+        # Initialize total predictions tensor
+        self.total_preds = torch.zeros((batch_size, 0, self.diar_model.sortformer_modules.n_spk), device=device)
+
+    def insert_silence(self, silence_duration: float):
+        """
+        Insert silence period by adjusting the global time offset.
+        
+        Args:
+            silence_duration: Duration of silence in seconds
+        """
+        with self.segment_lock:
+            self.global_time_offset += silence_duration
+        logger.debug(f"Inserted silence of {silence_duration:.2f}s, new offset: {self.global_time_offset:.2f}s")
+
+    async def diarize(self, pcm_array: np.ndarray):
+        """
+        Process audio data for diarization in streaming fashion.
+        
+        Args:
+            pcm_array: Audio data as numpy array
+        """
+        try:
+            if self.debug:
+                self.audio_buffer.append(pcm_array.copy())
+
+            threshold = int(self.chunk_duration_seconds * self.sample_rate)
+            
+            self.buffer_audio = np.concatenate([self.buffer_audio, pcm_array.copy()])
+            if not len(self.buffer_audio) >= threshold:
+                return
+            
+            audio = self.buffer_audio[:threshold]
+            self.buffer_audio = self.buffer_audio[threshold:]
+            
+            audio_signal_chunk = torch.tensor(audio).unsqueeze(0).to(self.diar_model.device)
+            audio_signal_length_chunk = torch.tensor([audio_signal_chunk.shape[1]]).to(self.diar_model.device)
+            
+            processed_signal_chunk, processed_signal_length_chunk = self.audio2mel.get_features(
+                audio_signal_chunk, audio_signal_length_chunk
+            )
+            
+            if self._previous_chunk_features is not None:
+                to_add = self._previous_chunk_features[:, :, -99:]
+                total_features = torch.concat([to_add, processed_signal_chunk], dim=2)
+            else:
+                total_features = processed_signal_chunk
+            
+            self._previous_chunk_features = processed_signal_chunk
+            
+            chunk_feat_seq_t = torch.transpose(total_features, 1, 2)
+            
+            with torch.inference_mode():
+                left_offset = 8 if self._chunk_index > 0 else 0
+                right_offset = 8
+                
+                self.streaming_state, self.total_preds = self.diar_model.forward_streaming_step(
+                    processed_signal=chunk_feat_seq_t,
+                    processed_signal_length=torch.tensor([chunk_feat_seq_t.shape[1]]),
+                    streaming_state=self.streaming_state,
+                    total_preds=self.total_preds,
+                    left_offset=left_offset,
+                    right_offset=right_offset,
+                )
+                
+            # Convert predictions to speaker segments
+            self._process_predictions()
+            
+            self._chunk_index += 1
+            
+        except Exception as e:
+            logger.error(f"Error in diarize: {e}")
+            raise
+            
+        # TODO: Handle case when stream ends with partial buffer (accumulated_duration > 0 but < chunk_duration_seconds)
+
+    def _process_predictions(self):
+        """Process model predictions and convert to speaker segments."""
+        try:
+            preds_np = self.total_preds[0].cpu().numpy()
+            active_speakers = np.argmax(preds_np, axis=1)
+            
+            if self._len_prediction is None:
+                self._len_prediction = len(active_speakers)
+            
+            # Get predictions for current chunk
+            frame_duration = self.chunk_duration_seconds / self._len_prediction
+            current_chunk_preds = active_speakers[-self._len_prediction:]
+            
+            with self.segment_lock:
+                # Process predictions into segments
+                base_time = self._chunk_index * self.chunk_duration_seconds + self.global_time_offset
+                
+                for idx, spk in enumerate(current_chunk_preds):
+                    start_time = base_time + idx * frame_duration
+                    end_time = base_time + (idx + 1) * frame_duration
+                    
+                    # Check if this continues the last segment or starts a new one
+                    if (self.speaker_segments and 
+                        self.speaker_segments[-1].speaker == spk and 
+                        abs(self.speaker_segments[-1].end - start_time) < frame_duration * 0.5):
+                        # Continue existing segment
+                        self.speaker_segments[-1].end = end_time
+                    else:
+                        
+                        # Create new segment
+                        self.speaker_segments.append(SpeakerSegment(
+                            speaker=spk,
+                            start=start_time,
+                            end=end_time
+                        ))
+                
+                # Update processed time
+                self.processed_time = max(self.processed_time, base_time + self.chunk_duration_seconds)
+                
+                logger.debug(f"Processed chunk {self._chunk_index}, total segments: {len(self.speaker_segments)}")
+                
+        except Exception as e:
+            logger.error(f"Error processing predictions: {e}")
+
+    def assign_speakers_to_tokens(self, tokens: list, use_punctuation_split: bool = False) -> list:
+        """
+        Assign speakers to tokens based on timing overlap with speaker segments.
+        
+        Args:
+            tokens: List of tokens with timing information
+            use_punctuation_split: Whether to use punctuation for boundary refinement
+            
+        Returns:
+            List of tokens with speaker assignments
+        """
+        with self.segment_lock:
+            segments = self.speaker_segments.copy()
+        
+        if not segments or not tokens:
+            logger.debug("No segments or tokens available for speaker assignment")
+            return tokens
+        
+        logger.debug(f"Assigning speakers to {len(tokens)} tokens using {len(segments)} segments")
+        use_punctuation_split = False
+        if not use_punctuation_split:
+            # Simple overlap-based assignment
+            for token in tokens:
+                token.speaker = -1  # Default to no speaker
+                for segment in segments:
+                    # Check for timing overlap
+                    if not (segment.end <= token.start or segment.start >= token.end):
+                        token.speaker = segment.speaker + 1  # Convert to 1-based indexing
+                        break
+        else:
+            # Use punctuation-aware assignment (similar to diart_backend)
+            tokens = self._add_speaker_to_tokens_with_punctuation(segments, tokens)
+        
+        return tokens
+
+    def _add_speaker_to_tokens_with_punctuation(self, segments: List[SpeakerSegment], tokens: list) -> list:
+        """
+        Assign speakers to tokens with punctuation-aware boundary adjustment.
+        
+        Args:
+            segments: List of speaker segments
+            tokens: List of tokens to assign speakers to
+            
+        Returns:
+            List of tokens with speaker assignments
+        """
+        punctuation_marks = {'.', '!', '?'}
+        punctuation_tokens = [token for token in tokens if token.text.strip() in punctuation_marks]
+        
+        # Convert segments to concatenated format
+        segments_concatenated = self._concatenate_speakers(segments)
+        
+        # Adjust segment boundaries based on punctuation
+        for ind, segment in enumerate(segments_concatenated):
+            for i, punctuation_token in enumerate(punctuation_tokens):
+                if punctuation_token.start > segment['end']:
+                    after_length = punctuation_token.start - segment['end']
+                    before_length = segment['end'] - punctuation_tokens[i - 1].end if i > 0 else float('inf')
+                    
+                    if before_length > after_length:
+                        segment['end'] = punctuation_token.start
+                        if i < len(punctuation_tokens) - 1 and ind + 1 < len(segments_concatenated):
+                            segments_concatenated[ind + 1]['begin'] = punctuation_token.start
+                    else:
+                        segment['end'] = punctuation_tokens[i - 1].end if i > 0 else segment['end']
+                        if i < len(punctuation_tokens) - 1 and ind - 1 >= 0:
+                            segments_concatenated[ind - 1]['begin'] = punctuation_tokens[i - 1].end
+                    break
+        
+        # Ensure non-overlapping tokens
+        last_end = 0.0
+        for token in tokens:
+            start = max(last_end + 0.01, token.start)
+            token.start = start
+            token.end = max(start, token.end)
+            last_end = token.end
+        
+        # Assign speakers based on adjusted segments
+        ind_last_speaker = 0
+        for segment in segments_concatenated:
+            for i, token in enumerate(tokens[ind_last_speaker:]):
+                if token.end <= segment['end']:
+                    token.speaker = segment['speaker']
+                    ind_last_speaker = i + 1
+                elif token.start > segment['end']:
+                    break
+        
+        return tokens
+
+    def _concatenate_speakers(self, segments: List[SpeakerSegment]) -> List[dict]:
+        """
+        Concatenate consecutive segments from the same speaker.
+        
+        Args:
+            segments: List of speaker segments
+            
+        Returns:
+            List of concatenated speaker segments
+        """
+        if not segments:
+            return []
+            
+        segments_concatenated = [{"speaker": segments[0].speaker + 1, "begin": segments[0].start, "end": segments[0].end}]
+        
+        for segment in segments[1:]:
+            speaker = segment.speaker + 1
+            if segments_concatenated[-1]['speaker'] != speaker:
+                segments_concatenated.append({"speaker": speaker, "begin": segment.start, "end": segment.end})
+            else:
+                segments_concatenated[-1]['end'] = segment.end
+                
+        return segments_concatenated
+
+    def get_segments(self) -> List[SpeakerSegment]:
+        """Get a copy of the current speaker segments."""
+        with self.segment_lock:
+            return self.speaker_segments.copy()
+
+    def clear_old_segments(self, older_than: float = 30.0):
+        """Clear segments older than the specified time."""
+        with self.segment_lock:
+            current_time = self.processed_time
+            self.speaker_segments = [
+                segment for segment in self.speaker_segments 
+                if current_time - segment.end < older_than
+            ]
+            logger.debug(f"Cleared old segments, remaining: {len(self.speaker_segments)}")
+
+    def close(self):
+        """Close the diarization system and clean up resources."""
+        logger.info("Closing SortformerDiarization")
+        with self.segment_lock:
+            self.speaker_segments.clear()
+        
+        if self.debug:
+            concatenated_audio = np.concatenate(self.audio_buffer)
+            audio_data_int16 = (concatenated_audio * 32767).astype(np.int16)                
+            with wave.open("diarization_audio.wav", "wb") as wav_file:
+                wav_file.setnchannels(1)  # mono audio
+                wav_file.setsampwidth(2)   # 2 bytes per sample (int16)
+                wav_file.setframerate(self.sample_rate)
+                wav_file.writeframes(audio_data_int16.tobytes())
+            logger.info(f"Saved {len(concatenated_audio)} samples to diarization_audio.wav")
+
+
+def extract_number(s: str) -> int:
+    """Extract number from speaker string (compatibility function)."""
+    import re
+    m = re.search(r'\d+', s)
+    return int(m.group()) if m else 0
+
+
+if __name__ == '__main__':
+    import asyncio
+    import librosa
+    
+    async def main():
+        """TEST ONLY."""
+        an4_audio = 'audio_test.mp3'
+        signal, sr = librosa.load(an4_audio, sr=16000)
+        signal = signal[:16000*30]
+
+        print("\n" + "=" * 50)
+        print("ground truth:")
+        print("Speaker 0: 0:00 - 0:09")
+        print("Speaker 1: 0:09 - 0:19") 
+        print("Speaker 2: 0:19 - 0:25")
+        print("Speaker 0: 0:25 - 0:30")
+        print("=" * 50)
+        
+        diarization = SortformerDiarization(sample_rate=16000)        
+        chunk_size = 1600
+        
+        for i in range(0, len(signal), chunk_size):
+            chunk = signal[i:i+chunk_size]
+            await diarization.diarize(chunk)
+            print(f"Processed chunk {i // chunk_size + 1}")
+        
+        segments = diarization.get_segments()
+        print("\nDiarization results:")
+        for segment in segments:
+            print(f"Speaker {segment.speaker}: {segment.start:.2f}s - {segment.end:.2f}s")
+    
+    asyncio.run(main())

whisperlivekit/diarization/sortformer_backend_offline.py

@@ -0,0 +1,205 @@
+import numpy as np
+import torch
+import logging
+
+from nemo.collections.asr.models import SortformerEncLabelModel
+from nemo.collections.asr.modules import AudioToMelSpectrogramPreprocessor
+import librosa
+
+logger = logging.getLogger(__name__)
+
+def load_model():
+
+    diar_model = SortformerEncLabelModel.from_pretrained("nvidia/diar_streaming_sortformer_4spk-v2")
+    diar_model.eval()
+
+    if torch.cuda.is_available():
+        diar_model.to(torch.device("cuda"))
+
+    #we target 1 second lag for the moment. chunk_len could be reduced.
+    diar_model.sortformer_modules.chunk_len = 10
+    diar_model.sortformer_modules.subsampling_factor = 10 #8 would be better ideally
+
+    diar_model.sortformer_modules.chunk_right_context = 0 #no.
+    diar_model.sortformer_modules.chunk_left_context = 10 #big so it compensiate the problem with no padding later.
+
+    diar_model.sortformer_modules.spkcache_len = 188
+    diar_model.sortformer_modules.fifo_len = 188
+    diar_model.sortformer_modules.spkcache_update_period = 144
+    diar_model.sortformer_modules.log = False
+    diar_model.sortformer_modules._check_streaming_parameters()
+
+
+    audio2mel = AudioToMelSpectrogramPreprocessor(
+            window_size= 0.025, 
+            normalize="NA",
+            n_fft=512,
+            features=128,
+            pad_to=0) #pad_to 16 works better than 0. On test audio, we detect a third speaker for 1 second with pad_to=0. To solve that : increase left context to 10.
+
+    return diar_model, audio2mel
+
+diar_model, audio2mel = load_model()
+
+class StreamingSortformerState:
+    """
+    This class creates a class instance that will be used to store the state of the
+    streaming Sortformer model.
+
+    Attributes:
+        spkcache (torch.Tensor): Speaker cache to store embeddings from start
+        spkcache_lengths (torch.Tensor): Lengths of the speaker cache
+        spkcache_preds (torch.Tensor): The speaker predictions for the speaker cache parts
+        fifo (torch.Tensor): FIFO queue to save the embedding from the latest chunks
+        fifo_lengths (torch.Tensor): Lengths of the FIFO queue
+        fifo_preds (torch.Tensor): The speaker predictions for the FIFO queue parts
+        spk_perm (torch.Tensor): Speaker permutation information for the speaker cache
+        mean_sil_emb (torch.Tensor): Mean silence embedding
+        n_sil_frames (torch.Tensor): Number of silence frames
+    """
+
+    spkcache = None  # Speaker cache to store embeddings from start
+    spkcache_lengths = None  #
+    spkcache_preds = None  # speaker cache predictions
+    fifo = None  # to save the embedding from the latest chunks
+    fifo_lengths = None
+    fifo_preds = None
+    spk_perm = None
+    mean_sil_emb = None
+    n_sil_frames = None
+
+
+def init_streaming_state(self, batch_size: int = 1, async_streaming: bool = False, device: torch.device = None):
+    """
+    Initializes StreamingSortformerState with empty tensors or zero-valued tensors.
+
+    Args:
+        batch_size (int): Batch size for tensors in streaming state
+        async_streaming (bool): True for asynchronous update, False for synchronous update
+        device (torch.device): Device for tensors in streaming state
+
+    Returns:
+        streaming_state (SortformerStreamingState): initialized streaming state
+    """
+    streaming_state = StreamingSortformerState()
+    if async_streaming:
+        streaming_state.spkcache = torch.zeros((batch_size, self.spkcache_len, self.fc_d_model), device=device)
+        streaming_state.spkcache_preds = torch.zeros((batch_size, self.spkcache_len, self.n_spk), device=device)
+        streaming_state.spkcache_lengths = torch.zeros((batch_size,), dtype=torch.long, device=device)
+        streaming_state.fifo = torch.zeros((batch_size, self.fifo_len, self.fc_d_model), device=device)
+        streaming_state.fifo_lengths = torch.zeros((batch_size,), dtype=torch.long, device=device)
+    else:
+        streaming_state.spkcache = torch.zeros((batch_size, 0, self.fc_d_model), device=device)
+        streaming_state.fifo = torch.zeros((batch_size, 0, self.fc_d_model), device=device)
+    streaming_state.mean_sil_emb = torch.zeros((batch_size, self.fc_d_model), device=device)
+    streaming_state.n_sil_frames = torch.zeros((batch_size,), dtype=torch.long, device=device)
+    return streaming_state
+
+
+def process_diarization(chunks):
+    """ 
+    what it does:
+    1. Preprocessing: Applies dithering and pre-emphasis (high-pass filter) if enabled
+    2. STFT: Computes the Short-Time Fourier Transform using:
+        - the window of window_size=0.025 --> size of a window : 400 samples
+        - the hop parameter : n_window_stride = 0.01 -> every 160 samples, a new window
+    3. Magnitude Calculation: Converts complex STFT output to magnitude spectrogram
+    4. Mel Conversion: Applies Mel filterbanks (128 filters in this case) to get Mel spectrogram
+    5. Logarithm: Takes the log of the Mel spectrogram (if `log=True`)
+    6. Normalization: Skips normalization since `normalize="NA"`
+    7. Padding: Pads the time dimension to a multiple of `pad_to` (default 16)    
+    """
+    previous_chunk = None
+    l_chunk_feat_seq_t = []
+    for chunk in chunks:
+        audio_signal_chunk = torch.tensor(chunk).unsqueeze(0).to(diar_model.device)
+        audio_signal_length_chunk = torch.tensor([audio_signal_chunk.shape[1]]).to(diar_model.device)
+        processed_signal_chunk, processed_signal_length_chunk = audio2mel.get_features(audio_signal_chunk, audio_signal_length_chunk)
+        if previous_chunk is not None:
+            to_add = previous_chunk[:, :, -99:]
+            total = torch.concat([to_add, processed_signal_chunk], dim=2)
+        else:
+            total = processed_signal_chunk
+        previous_chunk = processed_signal_chunk
+        l_chunk_feat_seq_t.append(torch.transpose(total, 1, 2))
+
+    batch_size = 1
+    streaming_state = init_streaming_state(diar_model.sortformer_modules,
+        batch_size = batch_size,
+        async_streaming = True,
+        device = diar_model.device
+    )
+    total_preds = torch.zeros((batch_size, 0, diar_model.sortformer_modules.n_spk), device=diar_model.device)
+
+    chunk_duration_seconds = diar_model.sortformer_modules.chunk_len * diar_model.sortformer_modules.subsampling_factor * diar_model.preprocessor._cfg.window_stride
+
+    l_speakers = [
+        {'start_time': 0,
+        'end_time': 0,
+        'speaker': 0
+        }
+    ]
+    len_prediction = None
+    left_offset = 0
+    right_offset = 8
+    for i, chunk_feat_seq_t in enumerate(l_chunk_feat_seq_t):
+        with torch.inference_mode():
+                streaming_state, total_preds = diar_model.forward_streaming_step(
+                    processed_signal=chunk_feat_seq_t,
+                    processed_signal_length=torch.tensor([chunk_feat_seq_t.shape[1]]),
+                    streaming_state=streaming_state,
+                    total_preds=total_preds,
+                    left_offset=left_offset,
+                    right_offset=right_offset,
+                )
+                left_offset = 8
+                preds_np = total_preds[0].cpu().numpy()
+                active_speakers = np.argmax(preds_np, axis=1)
+                if len_prediction is None:
+                    len_prediction = len(active_speakers) # we want to get the len of 1 prediction
+                frame_duration = chunk_duration_seconds / len_prediction
+                active_speakers = active_speakers[-len_prediction:]
+                for idx, spk in enumerate(active_speakers):
+                    if spk != l_speakers[-1]['speaker']:
+                        l_speakers.append(
+                            {'start_time': (i * chunk_duration_seconds + idx * frame_duration),
+                            'end_time': (i * chunk_duration_seconds + (idx + 1) * frame_duration),
+                            'speaker': spk
+                        })                    
+                    else:
+                        l_speakers[-1]['end_time'] = i * chunk_duration_seconds + (idx + 1) * frame_duration
+                    
+        
+        """
+        Should print
+        [{'start_time': 0, 'end_time': 8.72, 'speaker': 0}, 
+        {'start_time': 8.72, 'end_time': 18.88, 'speaker': 1},
+        {'start_time': 18.88, 'end_time': 24.96, 'speaker': 2},
+        {'start_time': 24.96, 'end_time': 31.68, 'speaker': 0}]
+        """
+    for speaker in l_speakers:
+        print(f"Speaker {speaker['speaker']}: {speaker['start_time']:.2f}s - {speaker['end_time']:.2f}s")    
+    
+
+if __name__ == '__main__':
+    
+    an4_audio = 'audio_test.mp3'
+    signal, sr = librosa.load(an4_audio, sr=16000)
+    signal = signal[:16000*30]
+    # signal = signal[:-(len(signal)%16000)]
+
+    print("\n" + "=" * 50)
+    print("Expected ground truth:")
+    print("Speaker 0: 0:00 - 0:09")
+    print("Speaker 1: 0:09 - 0:19") 
+    print("Speaker 2: 0:19 - 0:25")
+    print("Speaker 0: 0:25 - 0:30")
+    print("=" * 50)
+
+    chunk_size = 16000  # 1 second
+    chunks = []
+    for i in range(0, len(signal), chunk_size):
+        chunk = signal[i:i+chunk_size]
+        chunks.append(chunk)
+    
+    process_diarization(chunks)

whisperlivekit/download_simulstreaming_backend.py

@@ -1,32 +0,0 @@
-import os
-import requests
-import inspect
-
-def get_module_path():
-    return os.path.dirname(inspect.getfile(inspect.currentframe()))
-
-GITHUB_API_URL = "https://api.github.com/repos/ufal/SimulStreaming/contents/simul_whisper/whisper"
-RAW_BASE_URL = "https://raw.githubusercontent.com/ufal/SimulStreaming/main/simul_whisper/whisper"
-TARGET_DIR = os.path.join(get_module_path(), "simul_whisper", "whisper")
-
-def download_files_from_github(api_url, local_dir):
-    os.makedirs(local_dir, exist_ok=True)
-    response = requests.get(api_url)
-    response.raise_for_status()
-    items = response.json()
-    for item in items:
-        if item['type'] == 'file':
-            download_url = item['download_url']
-            file_name = item['name']
-            file_response = requests.get(download_url)
-            file_response.raise_for_status()
-            with open(os.path.join(local_dir, file_name), 'wb') as f:
-                f.write(file_response.content)
-        elif item['type'] == 'dir':
-            # Recursive call for subdirectories
-            download_files_from_github(item['url'], os.path.join(local_dir, item['name']))
-
-def download_simulstreaming_backend():
-    print(f"Downloading files into {TARGET_DIR} ...")
-    download_files_from_github(GITHUB_API_URL, TARGET_DIR)
-    print("✅ Download of SimulStreaming backend files completed successfully.")

whisperlivekit/ffmpeg_manager.py

@@ -143,7 +143,7 @@ class FFmpegManager:
         try:
             data = await asyncio.wait_for(
                 self.process.stdout.read(size),
-                timeout=5.0
+                timeout=20.0
             )
             return data
         except asyncio.TimeoutError:

whisperlivekit/parse_args.py

@@ -58,6 +58,14 @@ def parse_args():
         help="Hugging Face model ID for pyannote.audio embedding model.",
     )
 
+    parser.add_argument(
+        "--diarization-backend",
+        type=str,
+        default="sortformer",
+        choices=["sortformer", "diart"],
+        help="The diarization backend to use.",
+    )
+
     parser.add_argument(
         "--no-transcription",
         action="store_true",
@@ -74,7 +82,7 @@ def parse_args():
     parser.add_argument(
         "--model",
         type=str,
-        default="tiny",
+        default="small",
         help="Name size of the Whisper model to use (default: tiny). Suggested values: tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo. The model is automatically downloaded from the model hub if not present in model cache dir.",
     )
     
@@ -107,15 +115,15 @@ def parse_args():
     parser.add_argument(
         "--backend",
         type=str,
-        default="faster-whisper",
+        default="simulstreaming",
         choices=["faster-whisper", "whisper_timestamped", "mlx-whisper", "openai-api", "simulstreaming"],
         help="Load only this backend for Whisper processing.",
     )
     parser.add_argument(
-        "--vac",
+        "--no-vac",
         action="store_true",
         default=False,
-        help="Use VAC = voice activity controller. Recommended. Requires torch.",
+        help="Disable VAC = voice activity controller.",
     )
     parser.add_argument(
         "--vac-chunk-size", type=float, default=0.04, help="VAC sample size in seconds."
@@ -242,6 +250,14 @@ def parse_args():
         dest="model_path",
         help="Direct path to the SimulStreaming Whisper .pt model file. Overrides --model for SimulStreaming backend.",
     )
+    
+    simulstreaming_group.add_argument(
+        "--preloaded_model_count",
+        type=int,
+        default=1,
+        dest="preloaded_model_count",
+        help="Optional. Number of models to preload in memory to speed up loading (set up to the expected number of concurrent instances).",
+    )
 
     args = parser.parse_args()
     

whisperlivekit/remove_silences.py

@@ -0,0 +1,110 @@
+from whisperlivekit.timed_objects import ASRToken
+import re
+
+MIN_SILENCE_DURATION = 4 #in seconds
+END_SILENCE_DURATION = 8 #in seconds. you should keep it important to not have false positive when the model lag is important
+END_SILENCE_DURATION_VAC = 3 #VAC is good at detecting silences, but we want to skip the smallest silences
+
+def blank_to_silence(tokens):
+    full_string = ''.join([t.text for t in tokens])
+    patterns = [re.compile(r'(?:\s*\[BLANK_AUDIO\]\s*)+'), re.compile(r'(?:\s*\[typing\]\s*)+')]             
+    matches = []
+    for pattern in patterns:
+        for m in pattern.finditer(full_string):
+            matches.append({
+                'start': m.start(),
+                'end': m.end()
+            })
+    if matches:
+        # cleaned = pattern.sub(' ', full_string).strip()
+        # print("Cleaned:", cleaned)
+        cumulated_len = 0
+        silence_token = None
+        cleaned_tokens = []
+        for token in tokens:
+            if matches:
+                start = cumulated_len
+                end = cumulated_len + len(token.text)
+                cumulated_len = end
+                if start >= matches[0]['start'] and end <= matches[0]['end']:
+                    if silence_token: #previous token was already silence
+                        silence_token.start = min(silence_token.start, token.start)
+                        silence_token.end = max(silence_token.end, token.end)
+                    else: #new silence
+                        silence_token = ASRToken(
+                            start=token.start,
+                            end=token.end,
+                            speaker=-2,
+                            probability=0.95
+                        )
+                else:
+                    if silence_token: #there was silence but no more
+                        if silence_token.end - silence_token.start >= MIN_SILENCE_DURATION:
+                            cleaned_tokens.append(
+                                silence_token
+                            )
+                        silence_token = None
+                        matches.pop(0)
+                    cleaned_tokens.append(token)
+        # print(cleaned_tokens)    
+        return cleaned_tokens
+    return tokens
+
+def no_token_to_silence(tokens):
+    new_tokens = []
+    silence_token = None
+    for token in tokens:
+        if token.speaker == -2:
+            if new_tokens and new_tokens[-1].speaker == -2: #if token is silence and previous one too
+                new_tokens[-1].end = token.end
+            else:
+                new_tokens.append(token)
+            
+        last_end = new_tokens[-1].end if new_tokens else 0.0
+        if token.start - last_end >= MIN_SILENCE_DURATION: #if token is not silence but important gap
+            if new_tokens and new_tokens[-1].speaker == -2:
+                new_tokens[-1].end = token.start
+            else:
+                silence_token = ASRToken(
+                    start=last_end,
+                    end=token.start,
+                    speaker=-2,
+                    probability=0.95
+                    )
+                new_tokens.append(silence_token)
+        
+        if token.speaker != -2:
+            new_tokens.append(token)
+    return new_tokens
+            
+def ends_with_silence(tokens, buffer_transcription, buffer_diarization, current_time, vac_detected_silence):
+    if not tokens:
+        return [], buffer_transcription, buffer_diarization
+    last_token = tokens[-1]
+    if tokens and (
+        current_time - last_token.end >= END_SILENCE_DURATION 
+        or 
+        (current_time - last_token.end >= 3 and vac_detected_silence)
+        ):
+        if last_token.speaker == -2:
+            last_token.end = current_time
+        else:
+            tokens.append(
+                ASRToken(
+                    start=tokens[-1].end,
+                    end=current_time,
+                    speaker=-2,
+                    probability=0.95
+                )
+            )
+        buffer_transcription = "" # for whisperstreaming backend, we should probably validate the buffer has because of the silence
+        buffer_diarization  = ""
+    return tokens, buffer_transcription, buffer_diarization
+    
+
+def handle_silences(tokens, buffer_transcription, buffer_diarization, current_time, vac_detected_silence):
+    tokens = blank_to_silence(tokens) #useful for simulstreaming backend which tends to generate [BLANK_AUDIO] text
+    tokens = no_token_to_silence(tokens)
+    tokens, buffer_transcription, buffer_diarization = ends_with_silence(tokens, buffer_transcription, buffer_diarization, current_time, vac_detected_silence)
+    return tokens, buffer_transcription, buffer_diarization
+     

whisperlivekit/results_formater.py

@@ -0,0 +1,138 @@
+
+import logging
+from datetime import timedelta
+from whisperlivekit.remove_silences import handle_silences
+
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.DEBUG)
+
+PUNCTUATION_MARKS = {'.', '!', '?'}
+CHECK_AROUND = 4
+
+def format_time(seconds: float) -> str:
+    """Format seconds as HH:MM:SS."""
+    return str(timedelta(seconds=int(seconds)))
+
+
+def is_punctuation(token):
+    if token.text.strip() in PUNCTUATION_MARKS:
+        return True
+    return False
+
+def next_punctuation_change(i, tokens):
+    for ind in range(i+1, min(len(tokens), i+CHECK_AROUND+1)):
+        if is_punctuation(tokens[ind]):
+            return ind        
+    return None
+
+def next_speaker_change(i, tokens, speaker):
+    for ind in range(i-1, max(0, i-CHECK_AROUND)-1, -1):
+        token = tokens[ind]
+        if is_punctuation(token):
+            break
+        if token.speaker != speaker:
+            return ind, token.speaker
+    return None, speaker
+    
+
+def new_line(
+    token,
+    speaker,
+    last_end_diarized,
+    debug_info = ""
+):
+    return {
+            "speaker": int(speaker),
+            "text": token.text + debug_info,
+            "beg": format_time(token.start),
+            "end": format_time(token.end),
+            "diff": round(token.end - last_end_diarized, 2)
+    }
+
+
+def append_token_to_last_line(lines, sep, token, debug_info, last_end_diarized):
+    if token.text:
+        lines[-1]["text"] += sep + token.text + debug_info
+        lines[-1]["end"] = format_time(token.end)
+        lines[-1]["diff"] = round(token.end - last_end_diarized, 2)
+            
+
+def format_output(state, silence, current_time, diarization, debug):
+    tokens = state["tokens"]
+    buffer_transcription = state["buffer_transcription"]
+    buffer_diarization = state["buffer_diarization"]
+    end_attributed_speaker = state["end_attributed_speaker"]
+    sep = state["sep"]
+    
+    previous_speaker = -1
+    lines = []
+    last_end_diarized = 0
+    undiarized_text = []
+    tokens, buffer_transcription, buffer_diarization = handle_silences(tokens, buffer_transcription, buffer_diarization, current_time, silence)
+    last_punctuation = None
+    for i, token in enumerate(tokens):
+        speaker = token.speaker
+        
+        if not diarization and speaker == -1: #Speaker -1 means no attributed by diarization. In the frontend, it should appear under 'Speaker 1'
+            speaker = 1
+        if diarization and not tokens[-1].speaker == -2:
+            if (speaker in [-1, 0]) and token.end >= end_attributed_speaker:
+                undiarized_text.append(token.text)
+                continue
+            elif (speaker in [-1, 0]) and token.end < end_attributed_speaker:
+                speaker = previous_speaker
+            if speaker not in [-1, 0]:
+                last_end_diarized = max(token.end, last_end_diarized)
+
+        debug_info = ""
+        if debug:
+            debug_info = f"[{format_time(token.start)} : {format_time(token.end)}]"
+            
+        if not lines:
+            lines.append(new_line(token, speaker, last_end_diarized, debug_info = ""))
+            continue
+        else:
+            previous_speaker = lines[-1]['speaker']
+        
+        if is_punctuation(token):
+            last_punctuation = i
+            
+        
+        if last_punctuation == i-1:
+            if speaker != previous_speaker:
+                # perfect, diarization perfectly aligned
+                lines.append(new_line(token, speaker, last_end_diarized, debug_info = ""))
+                last_punctuation, next_punctuation = None, None
+                continue
+            
+            speaker_change_pos, new_speaker = next_speaker_change(i, tokens, speaker)
+            if speaker_change_pos:
+                # Corrects delay:
+                # That was the idea. Okay haha |SPLIT SPEAKER| that's a good one 
+                # should become:
+                # That was the idea. |SPLIT SPEAKER| Okay haha that's a good one 
+                lines.append(new_line(token, new_speaker, last_end_diarized, debug_info = ""))
+            else:
+                # No speaker change to come
+                append_token_to_last_line(lines, sep, token, debug_info, last_end_diarized)
+            continue
+        
+
+        if speaker != previous_speaker:
+            if speaker == -2 or previous_speaker == -2: #silences can happen anytime
+                lines.append(new_line(token, speaker, last_end_diarized, debug_info = ""))
+                continue
+            elif next_punctuation_change(i, tokens):
+                # Corrects advance:
+                # Are you |SPLIT SPEAKER| okay? yeah, sure. Absolutely 
+                # should become:
+                # Are you okay? |SPLIT SPEAKER| yeah, sure. Absolutely 
+                append_token_to_last_line(lines, sep, token, debug_info, last_end_diarized)
+                continue
+            else: #we create a new speaker, but that's no ideal. We are not sure about the split. We prefer to append to previous line
+                # lines.append(new_line(token, speaker, last_end_diarized, debug_info = ""))
+                pass
+            
+        append_token_to_last_line(lines, sep, token, debug_info, last_end_diarized)
+    return lines, undiarized_text, buffer_transcription, '' 
+

whisperlivekit/simul_whisper/__init__.py

@@ -0,0 +1,6 @@
+from .backend import SimulStreamingASR, SimulStreamingOnlineProcessor
+
+__all__ = [
+    "SimulStreamingASR",
+    "SimulStreamingOnlineProcessor",
+]

whisperlivekit/simul_whisper/backend.py

@@ -0,0 +1,315 @@
+import sys
+import numpy as np
+import logging
+from typing import List, Tuple, Optional
+import logging
+from whisperlivekit.timed_objects import ASRToken, Transcript
+from whisperlivekit.warmup import load_file
+from whisperlivekit.simul_whisper.license_simulstreaming import SIMULSTREAMING_LICENSE
+from .whisper import load_model, tokenizer
+from .whisper.audio import TOKENS_PER_SECOND
+
+import os
+import gc
+logger = logging.getLogger(__name__)
+
+try:
+    import torch
+    from whisperlivekit.simul_whisper.config import AlignAttConfig
+    from whisperlivekit.simul_whisper.simul_whisper import PaddedAlignAttWhisper
+    from whisperlivekit.simul_whisper.whisper import tokenizer
+except ImportError as e:
+    raise ImportError(
+        """SimulStreaming dependencies are not available.
+        Please install WhisperLiveKit using pip install "whisperlivekit[simulstreaming]".""")
+
+# TOO_MANY_REPETITIONS = 3
+
+class SimulStreamingOnlineProcessor:
+    SAMPLING_RATE = 16000
+
+    def __init__(
+        self,
+        asr,
+        logfile=sys.stderr,
+        warmup_file=None
+    ):        
+        self.asr = asr
+        self.logfile = logfile
+        self.end = 0.0
+        self.global_time_offset = 0.0
+        
+        self.committed: List[ASRToken] = []
+        self.last_result_tokens: List[ASRToken] = []
+        self.load_new_backend()
+        if asr.tokenizer:
+            self.model.tokenizer = asr.tokenizer
+
+    def load_new_backend(self):
+        model = self.asr.get_new_model_instance()
+        self.model = PaddedAlignAttWhisper(
+            cfg=self.asr.cfg,
+            loaded_model=model)
+
+    def insert_silence(self, silence_duration, offset):
+        """
+        If silences are > 5s, we do a complete context clear. Otherwise, we just insert a small silence and shift the last_attend_frame
+        """
+        if silence_duration < 5:
+            gap_silence = torch.zeros(int(16000*silence_duration))
+            self.model.insert_audio(gap_silence)
+            # self.global_time_offset += silence_duration
+        else:
+            self.process_iter(is_last=True) #we want to totally process what remains in the buffer.
+            self.model.refresh_segment(complete=True)
+            self.global_time_offset += silence_duration + offset
+
+
+        
+    def insert_audio_chunk(self, audio: np.ndarray, audio_stream_end_time):
+        """Append an audio chunk to be processed by SimulStreaming."""
+            
+        # Convert numpy array to torch tensor
+        audio_tensor = torch.from_numpy(audio).float()
+        self.end = audio_stream_end_time #Only to be aligned with what happens in whisperstreaming backend.
+        self.model.insert_audio(audio_tensor)
+
+    def get_buffer(self):
+        return Transcript(
+            start=None, 
+            end=None, 
+            text='', 
+            probability=None
+        )
+
+    def timestamped_text(self, tokens, generation):
+        """
+        generate timestamped text from tokens and generation data.
+        
+        args:
+            tokens: List of tokens to process
+            generation: Dictionary containing generation progress and optionally results
+            
+        returns:
+            List of tuples containing (start_time, end_time, word) for each word
+        """
+        FRAME_DURATION = 0.02    
+        if "result" in generation:
+            split_words = generation["result"]["split_words"]
+            split_tokens = generation["result"]["split_tokens"]
+        else:
+            split_words, split_tokens = self.model.tokenizer.split_to_word_tokens(tokens)
+        progress = generation["progress"]
+        frames = [p["most_attended_frames"][0] for p in progress]
+        absolute_timestamps = [p["absolute_timestamps"][0] for p in progress]
+        tokens_queue = tokens.copy()
+        timestamped_words = []
+        
+        for word, word_tokens in zip(split_words, split_tokens):
+            # start_frame = None
+            # end_frame = None
+            for expected_token in word_tokens:
+                if not tokens_queue or not frames:
+                    raise ValueError(f"Insufficient tokens or frames for word '{word}'")
+                    
+                actual_token = tokens_queue.pop(0)
+                current_frame = frames.pop(0)
+                current_timestamp = absolute_timestamps.pop(0)
+                if actual_token != expected_token:
+                    raise ValueError(
+                        f"Token mismatch: expected '{expected_token}', "
+                        f"got '{actual_token}' at frame {current_frame}"
+                    )
+                # if start_frame is None:
+                #     start_frame = current_frame
+                # end_frame = current_frame
+            # start_time = start_frame * FRAME_DURATION
+            # end_time = end_frame * FRAME_DURATION
+            start_time = current_timestamp
+            end_time = current_timestamp + 0.1
+            timestamp_entry = (start_time, end_time, word)
+            timestamped_words.append(timestamp_entry)
+            logger.debug(f"TS-WORD:\t{start_time:.2f}\t{end_time:.2f}\t{word}")
+        return timestamped_words
+
+    def process_iter(self, is_last=False) -> Tuple[List[ASRToken], float]:
+        """
+        Process accumulated audio chunks using SimulStreaming.
+        
+        Returns a tuple: (list of committed ASRToken objects, float representing the audio processed up to time).
+        """
+        try:
+            tokens, generation_progress = self.model.infer(is_last=is_last)
+            ts_words = self.timestamped_text(tokens, generation_progress)
+            
+            new_tokens = []
+            for ts_word in ts_words:
+                
+                start, end, word = ts_word
+                token = ASRToken(
+                    start=start,
+                    end=end,
+                    text=word,
+                    probability=0.95  # fake prob. Maybe we can extract it from the model?
+                ).with_offset(
+                    self.global_time_offset
+                )
+                new_tokens.append(token)
+                
+            # identical_tokens = 0
+            # n_new_tokens = len(new_tokens)
+            # if n_new_tokens:
+            
+            self.committed.extend(new_tokens)
+            
+            # if token in self.committed:
+            #     pos = len(self.committed) - 1 - self.committed[::-1].index(token)
+            # if pos:
+            #     for i in range(len(self.committed) - n_new_tokens, -1, -n_new_tokens):
+            #         commited_segment = self.committed[i:i+n_new_tokens]
+            #         if commited_segment == new_tokens:
+            #             identical_segments +=1
+            #             if identical_tokens >= TOO_MANY_REPETITIONS:
+            #                 logger.warning('Too many repetition, model is stuck. Load a new one')
+            #                 self.committed = self.committed[:i]
+            #                 self.load_new_backend()
+            #                 return [], self.end
+
+            # pos = self.committed.rindex(token)
+
+            
+            
+            return new_tokens, self.end
+
+            
+        except Exception as e:
+            logger.exception(f"SimulStreaming processing error: {e}")
+            return [], self.end
+
+    def warmup(self, audio, init_prompt=""):
+        """Warmup the SimulStreaming model."""
+        try:
+            self.model.insert_audio(audio)
+            self.model.infer(True)
+            self.model.refresh_segment(complete=True)
+            logger.info("SimulStreaming model warmed up successfully")
+        except Exception as e:
+            logger.exception(f"SimulStreaming warmup failed: {e}")
+
+    def __del__(self):
+        # free the model and add a new model to stack.
+        # del self.model
+        gc.collect()
+        torch.cuda.empty_cache()
+        # self.asr.new_model_to_stack()
+        self.model.remove_hooks()
+
+class SimulStreamingASR():
+    """SimulStreaming backend with AlignAtt policy."""
+    sep = ""
+
+    def __init__(self, lan, modelsize=None, cache_dir=None, model_dir=None, logfile=sys.stderr, **kwargs):
+        logger.warning(SIMULSTREAMING_LICENSE)
+        self.logfile = logfile
+        self.transcribe_kargs = {}
+        self.original_language = None if lan == "auto" else lan
+        
+        self.model_path = kwargs.get('model_path', './large-v3.pt')
+        self.frame_threshold = kwargs.get('frame_threshold', 25)
+        self.audio_max_len = kwargs.get('audio_max_len', 20.0)
+        self.audio_min_len = kwargs.get('audio_min_len', 0.0)
+        self.segment_length = kwargs.get('segment_length', 0.5)
+        self.beams = kwargs.get('beams', 1)
+        self.decoder_type = kwargs.get('decoder_type', 'greedy' if self.beams == 1 else 'beam')
+        self.task = kwargs.get('task', 'transcribe')
+        self.cif_ckpt_path = kwargs.get('cif_ckpt_path', None)
+        self.never_fire = kwargs.get('never_fire', False)
+        self.init_prompt = kwargs.get('init_prompt', None)
+        self.static_init_prompt = kwargs.get('static_init_prompt', None)
+        self.max_context_tokens = kwargs.get('max_context_tokens', None)
+        self.warmup_file = kwargs.get('warmup_file', None)
+        self.preload_model_count = kwargs.get('preload_model_count', 1)
+        
+        if model_dir is not None:
+            self.model_path = model_dir
+        elif modelsize is not None:
+            model_mapping = {
+                'tiny': './tiny.pt',
+                'base': './base.pt',
+                'small': './small.pt',
+                'medium': './medium.pt',
+                'medium.en': './medium.en.pt',
+                'large-v1': './large-v1.pt',
+                'base.en': './base.en.pt',
+                'small.en': './small.en.pt',
+                'tiny.en': './tiny.en.pt',
+                'large-v2': './large-v2.pt',
+                'large-v3': './large-v3.pt',
+                'large': './large-v3.pt'
+            }
+            self.model_path = model_mapping.get(modelsize, f'./{modelsize}.pt')
+        
+        # Set up tokenizer for translation if needed
+        if self.task == "translate":
+            self.tokenizer = self.set_translate_task()
+        else:
+            self.tokenizer = None
+        self.cfg = AlignAttConfig(
+                model_path=self.model_path,
+                segment_length=self.segment_length,
+                frame_threshold=self.frame_threshold,
+                language=self.original_language,
+                audio_max_len=self.audio_max_len,
+                audio_min_len=self.audio_min_len,
+                cif_ckpt_path=self.cif_ckpt_path,
+                decoder_type="beam",
+                beam_size=self.beams,
+                task=self.task,
+                never_fire=self.never_fire,
+                init_prompt=self.init_prompt,
+                max_context_tokens=self.max_context_tokens,
+                static_init_prompt=self.static_init_prompt,
+        )  
+        
+        self.model_name = os.path.basename(self.cfg.model_path).replace(".pt", "")
+        self.model_path = os.path.dirname(os.path.abspath(self.cfg.model_path))
+        self.models = [self.load_model() for i in range(self.preload_model_count)]
+    
+
+
+
+    def load_model(self):
+        whisper_model = load_model(name=self.model_name, download_root=self.model_path)
+        warmup_audio = load_file(self.warmup_file)
+        whisper_model.transcribe(warmup_audio, language=self.original_language)
+        return whisper_model
+    
+    def get_new_model_instance(self):
+        """
+        SimulStreaming cannot share the same backend because it uses global forward hooks on the attention layers.
+        Therefore, each user requires a separate model instance, which can be memory-intensive. To maintain speed, we preload the models into memory.
+        """
+        if len(self.models) == 0:
+            self.models.append(self.load_model())
+        new_model = self.models.pop()
+        return new_model
+        # self.models[0]
+
+    def new_model_to_stack(self):
+        self.models.append(self.load_model())
+        
+
+    def set_translate_task(self):
+        """Set up translation task."""
+        return tokenizer.get_tokenizer(
+            multilingual=True,
+            language=self.model.cfg.language,
+            num_languages=self.model.model.num_languages,
+            task="translate"
+        )
+
+    def transcribe(self, audio):
+        """
+        Warmup is done directly in load_model
+        """
+        pass

whisperlivekit/simul_whisper/config.py

@@ -8,7 +8,7 @@ class SimulWhisperConfig:
     '''Options that are common for all simul policies that could be implemented in SimulWhisper.'''
     model_path: str
     language: str = field(default="zh")
-    nonspeech_prob: float = 1.0
+    nonspeech_prob: float = 0.5
     audio_min_len: float = 1.0
     decoder_type: Literal["greedy","beam"] = "greedy"
     beam_size: int = 5
@@ -24,6 +24,6 @@ class AlignAttConfig(SimulWhisperConfig):
     segment_length: float = field(default=1.0, metadata = {"help": "in second"})
     frame_threshold: int = 4
     rewind_threshold: int = 200
-    audio_max_len: float = 30.0
+    audio_max_len: float = 20.0
     cif_ckpt_path: str = ""
     never_fire: bool = False

whisperlivekit/simul_whisper/license_simulstreaming.py

@@ -1,18 +1,5 @@
 SIMULSTREAMING_LICENSE = f"""
-{"*"*80}
-SimulStreaming (https://github.com/ufal/SimulStreaming) is dual-licensed:
-
-🔹 Non-Commercial Use
-You may use SimulStreaming under the PolyForm Noncommercial License 1.0.0 if you obtain the code through the GitHub repository.  This license is free of charge and comes with no obligations for non-commercial users.
-
-🔸 Commercial Use
-Understanding who uses SimulStreaming commercially helps us improve and
-prioritize development. Therefore, we want to require registration of those who acquire a commercial licence.
-We plan to make the commercial licenceses affordable to SMEs and individuals. We are considering to provide commercial licenses either for free or for symbolic one-time fee, and maybe also provide additional support. You can share your preference via the questionnaire https://forms.cloud.microsoft/e/7tCxb4gJfB.
-You can also leave your contact there: https://forms.cloud.microsoft/e/7tCxb4gJfB to be notified when the commercial licenses become
-available.
-
-✉️ Contact
-Dominik Macháček (https://ufal.mff.cuni.cz/dominik-machacek/), machacek@ufal.mff.cuni.cz
-{"*"*80}
+SimulStreaming backend is dual-licensed:
+• Non-Commercial Use: PolyForm Noncommercial License 1.0.0.
+• Commercial Use: Check SimulStreaming README (github.com/ufal/SimulStreaming) for more details.
 """

whisperlivekit/simul_whisper/simul_whisper.py

@@ -15,7 +15,7 @@ from .beam import BeamPyTorchInference
 from .eow_detection import fire_at_boundary, load_cif
 import os
 
-from token_buffer import TokenBuffer
+from .token_buffer import TokenBuffer
 
 import numpy as np
 from .generation_progress import *
@@ -33,11 +33,14 @@ import wave
 # - prompt -- static vs. non-static
 # - context
 class PaddedAlignAttWhisper:
-    def __init__(self, cfg: AlignAttConfig) -> None:
+    def __init__(self, cfg: AlignAttConfig, loaded_model=None) -> None:
         self.log_segments = 0
         model_name = os.path.basename(cfg.model_path).replace(".pt", "")
         model_path = os.path.dirname(os.path.abspath(cfg.model_path))
-        self.model = load_model(name=model_name, download_root=model_path)
+        if loaded_model:
+            self.model = loaded_model
+        else:
+            self.model = load_model(name=model_name, download_root=model_path)
 
         logger.info(f"Model dimensions: {self.model.dims}")
 
@@ -53,6 +56,7 @@ class PaddedAlignAttWhisper:
         self.max_text_len = self.model.dims.n_text_ctx
         self.num_decoder_layers = len(self.model.decoder.blocks)
         self.cfg = cfg
+        self.l_hooks = []
 
         # model to detect end-of-word boundary at the end of the segment
         self.CIFLinear, self.always_fire, self.never_fire = load_cif(cfg,
@@ -66,7 +70,8 @@ class PaddedAlignAttWhisper:
             t = F.softmax(net_output[1], dim=-1)
             self.dec_attns.append(t.squeeze(0))
         for b in self.model.decoder.blocks:
-            b.cross_attn.register_forward_hook(layer_hook)
+            hook = b.cross_attn.register_forward_hook(layer_hook)
+            self.l_hooks.append(hook)
         
         self.kv_cache = {}
         def kv_hook(module: torch.nn.Linear, _, net_output: torch.Tensor):
@@ -79,10 +84,13 @@ class PaddedAlignAttWhisper:
             return self.kv_cache[module.cache_id] 
 
         for i,b in enumerate(self.model.decoder.blocks):
-            b.attn.key.register_forward_hook(kv_hook)
-            b.attn.value.register_forward_hook(kv_hook)
-            b.cross_attn.key.register_forward_hook(kv_hook)
-            b.cross_attn.value.register_forward_hook(kv_hook)
+            hooks = [
+                b.attn.key.register_forward_hook(kv_hook),
+                b.attn.value.register_forward_hook(kv_hook),
+                b.cross_attn.key.register_forward_hook(kv_hook),
+                b.cross_attn.value.register_forward_hook(kv_hook),
+            ]
+            self.l_hooks.extend(hooks)
 
         self.align_source = {}
         self.num_align_heads = 0
@@ -117,6 +125,7 @@ class PaddedAlignAttWhisper:
         self.init_tokens()
         
         self.last_attend_frame = -self.cfg.rewind_threshold
+        self.cumulative_time_offset = 0.0
 
         if self.cfg.max_context_tokens is None:
             self.max_context_tokens = self.max_text_len
@@ -136,6 +145,11 @@ class PaddedAlignAttWhisper:
             self.inference.kv_cache = self.kv_cache
 
             self.token_decoder = BeamSearchDecoder(inference=self.inference, eot=self.tokenizer.eot, beam_size=cfg.beam_size)
+            
+    def remove_hooks(self):
+        print('remove hook')
+        for hook in self.l_hooks:
+            hook.remove()
 
     def create_tokenizer(self, language=None):
         self.tokenizer = tokenizer.get_tokenizer(
@@ -207,6 +221,7 @@ class PaddedAlignAttWhisper:
         self.init_tokens()
         self.last_attend_frame = -self.cfg.rewind_threshold       
         self.detected_language = None
+        self.cumulative_time_offset = 0.0
         self.init_context()
         logger.debug(f"Context: {self.context}")
         if not complete and len(self.segments) > 2:
@@ -274,8 +289,9 @@ class PaddedAlignAttWhisper:
             removed_len = self.segments[0].shape[0] / 16000
             segments_len -= removed_len
             self.last_attend_frame -= int(TOKENS_PER_SECOND*removed_len)
+            self.cumulative_time_offset += removed_len  # Track cumulative time removed
             self.segments = self.segments[1:]
-            logger.debug(f"remove segments: {len(self.segments)} {len(self.tokens)}")
+            logger.debug(f"remove segments: {len(self.segments)} {len(self.tokens)}, cumulative offset: {self.cumulative_time_offset:.2f}s")
             if len(self.tokens) > 1:
                 self.context.append_token_ids(self.tokens[1][0,:])
                 self.tokens = [self.initial_tokens] + self.tokens[2:]
@@ -491,7 +507,13 @@ class PaddedAlignAttWhisper:
             # for each beam, the most attended frame is:
             most_attended_frames = torch.argmax(attn_of_alignment_heads[:,-1,:], dim=-1)
             generation_progress_loop.append(("most_attended_frames",most_attended_frames.clone().tolist()))
+            
+            # Calculate absolute timestamps accounting for cumulative offset
+            absolute_timestamps = [(frame * 0.02 + self.cumulative_time_offset) for frame in most_attended_frames.tolist()]
+            generation_progress_loop.append(("absolute_timestamps", absolute_timestamps))
+            
             logger.debug(str(most_attended_frames.tolist()) + " most att frames")
+            logger.debug(f"Absolute timestamps: {absolute_timestamps} (offset: {self.cumulative_time_offset:.2f}s)")
 
             most_attended_frame = most_attended_frames[0].item()
 
@@ -596,4 +618,4 @@ class PaddedAlignAttWhisper:
         
         self._clean_cache()
 
-        return new_hypothesis, generation
+        return new_hypothesis, generation

whisperlivekit/timed_objects.py

@@ -29,4 +29,8 @@ class SpeakerSegment(TimedText):
     """Represents a segment of audio attributed to a specific speaker.
     No text nor probability is associated with this segment.
     """
-    pass
+    pass
+
+@dataclass
+class Silence():
+    duration: float

whisperlivekit/token_buffer.py

@@ -1,73 +0,0 @@
-import torch
-import sys
-class TokenBuffer:
-
-    def __init__(self, text="", tokenizer=None, device=None, prefix_token_ids=[]):
-        self.text = text
-        self.prefix_token_ids = prefix_token_ids
-        self.tokenizer = tokenizer
-        self.device = device
-
-    def as_token_ids(self, tokenizer=None):
-
-        if tokenizer is None:
-            tokenizer = self.tokenizer
-        if tokenizer is None:
-            raise ValueError("Tokenizer is not set.") 
-        return self.prefix_token_ids + tokenizer.encode(self.text)
-
-    def as_tensor(self, device=None):
-        if device is None:
-            device = self.device
-        if device is None:
-            raise ValueError("Device is not set.")
-        tok_ids = self.as_token_ids()
-        return torch.tensor(tok_ids, 
-                     dtype=torch.long, device=device).unsqueeze(0)
-
-    def as_tensor_beam(self, beam, device=None):
-        t = self.as_tensor(device=device)
-        return t.repeat_interleave(beam, dim=0)
-
-
-    def as_text(self):
-        return self.text
-
-    @staticmethod
-    def empty(*a, **kw):
-        return TokenBuffer(*a,**kw)
-
-    @staticmethod
-    def from_text(text, *a, **kw):
-        return TokenBuffer(*a, text=text, **kw)
-    
-    def is_empty(self):
-        return self.text is None or self.text == ""
-
-    def trim_words(self, num=1, after=0):
-        '''
-        num: how many words to trim from the beginning
-        after: how many characters to skip (length of the static prompt)
-        '''
-        tokenizer = self.tokenizer
-        assert tokenizer is not None, "Tokenizer is not set."
-
-        ids = tokenizer.encode(self.text[after:])
-        words, wids = self.tokenizer.split_to_word_tokens(ids)
-        print(words, file=sys.stderr)
-        print(wids, file=sys.stderr)
-        if not words:
-            return 0
-        self.text = self.text[:after] + "".join(words[num:])
-        return sum(len(wi) for wi in wids[:num])
-
-    def append_token_ids(self, token_ids):
-        tokenizer = self.tokenizer
-        assert tokenizer is not None, "Tokenizer is not set."
-        self.text += self.tokenizer.decode(token_ids)
-
-    def as_split_word_tokens(self):
-        tokenizer = self.tokenizer
-        assert tokenizer is not None, "Tokenizer is not set."
-        ids = tokenizer.encode(self.text)
-        return tokenizer.split_to_word_tokens(ids)

whisperlivekit/trail_repetition.py

@@ -0,0 +1,60 @@
+from typing import Sequence, Callable, Any, Optional, Dict
+
+def _detect_tail_repetition(
+    seq: Sequence[Any],
+    key: Callable[[Any], Any] = lambda x: x,  # extract comparable value
+    min_block: int = 1,                       # set to 2 to ignore 1-token loops like "."
+    max_tail: int = 300,                      # search window from the end for speed
+    prefer: str = "longest",                  # "longest" coverage or "smallest" block
+) -> Optional[Dict]:
+    vals = [key(x) for x in seq][-max_tail:]
+    n = len(vals)
+    best = None
+
+    # try every possible block length
+    for b in range(min_block, n // 2 + 1):
+        block = vals[-b:]
+        # count how many times this block repeats contiguously at the very end
+        count, i = 0, n
+        while i - b >= 0 and vals[i - b:i] == block:
+            count += 1
+            i -= b
+
+        if count >= 2:
+            cand = {
+                "block_size": b,
+                "count": count,
+                "start_index": len(seq) - count * b,  # in original seq
+                "end_index": len(seq),
+            }
+            if (best is None or
+                (prefer == "longest" and count * b > best["count"] * best["block_size"]) or
+                (prefer == "smallest" and b < best["block_size"])):
+                best = cand
+    return best
+
+def trim_tail_repetition(
+    seq: Sequence[Any],
+    key: Callable[[Any], Any] = lambda x: x,
+    min_block: int = 1,
+    max_tail: int = 300,
+    prefer: str = "longest",
+    keep: int = 1,  # how many copies of the repeating block to keep at the end (0 or 1 are common)
+):
+    """
+    Returns a new sequence with repeated tail trimmed.
+    keep=1 -> keep a single copy of the repeated block.
+    keep=0 -> remove all copies of the repeated block.
+    """
+    rep = _detect_tail_repetition(seq, key, min_block, max_tail, prefer)
+    if not rep:
+        return seq, False  # nothing to trim
+
+    b, c = rep["block_size"], rep["count"]
+    if keep < 0:
+        keep = 0
+    if keep >= c:
+        return seq, False  # nothing to trim (already <= keep copies)
+    # new length = total - (copies_to_remove * block_size)
+    new_len = len(seq) - (c - keep) * b
+    return seq[:new_len], True

whisperlivekit/warmup.py

@@ -0,0 +1,62 @@
+
+import logging
+
+logger = logging.getLogger(__name__)
+
+def load_file(warmup_file=None, timeout=5):
+    import os
+    import tempfile
+    import librosa
+        
+    if warmup_file is None:
+        # Download JFK sample if not already present
+        jfk_url = "https://github.com/ggerganov/whisper.cpp/raw/master/samples/jfk.wav"
+        temp_dir = tempfile.gettempdir()
+        warmup_file = os.path.join(temp_dir, "whisper_warmup_jfk.wav")
+        
+        if not os.path.exists(warmup_file):
+            logger.debug(f"Downloading warmup file from {jfk_url}")
+            print(f"Downloading warmup file from {jfk_url}")
+            import time
+            import urllib.request
+            import urllib.error
+            import socket
+            
+            original_timeout = socket.getdefaulttimeout()
+            socket.setdefaulttimeout(timeout)
+            
+            start_time = time.time()
+            try:
+                urllib.request.urlretrieve(jfk_url, warmup_file)
+                logger.debug(f"Download successful in {time.time() - start_time:.2f}s")
+            except (urllib.error.URLError, socket.timeout) as e:
+                logger.warning(f"Download failed: {e}. Proceeding without warmup.")
+                return False
+            finally:
+                socket.setdefaulttimeout(original_timeout)
+    elif not warmup_file:
+        return False 
+    
+    if not warmup_file or not os.path.exists(warmup_file) or os.path.getsize(warmup_file) == 0:
+        logger.warning(f"Warmup file {warmup_file} invalid or missing.")
+        return False
+    
+    try:
+        audio, sr = librosa.load(warmup_file, sr=16000)
+    except Exception as e:
+        logger.warning(f"Failed to load audio file: {e}")
+        return False
+    return audio
+
+def warmup_asr(asr, warmup_file=None, timeout=5):
+    """
+    Warmup the ASR model by transcribing a short audio file.
+    """
+    audio = load_file(warmup_file=None, timeout=5)
+    asr.transcribe(audio)
+    logger.info("ASR model is warmed up")
+    
+def warmup_online(online, warmup_file=None, timeout=5):
+    audio = load_file(warmup_file=None, timeout=5)
+    online.warmup(audio)
+    logger.warning("ASR is warmed up")

whisperlivekit/web/live_transcription.css

@@ -0,0 +1,402 @@
+:root {
+  --bg: #ffffff;
+  --text: #111111;
+  --muted: #666666;
+  --border: #e5e5e5;
+  --chip-bg: rgba(0, 0, 0, 0.04);
+  --chip-text: #000000;
+  --spinner-border: #8d8d8d5c;
+  --spinner-top: #b0b0b0;
+  --silence-bg: #f3f3f3;
+  --loading-bg: rgba(255, 77, 77, 0.06);
+  --button-bg: #ffffff;
+  --button-border: #e9e9e9;
+  --wave-stroke: #000000;
+  --label-dia-text: #868686;
+  --label-trans-text: #111111;
+}
+
+@media (prefers-color-scheme: dark) {
+  :root:not([data-theme="light"]) {
+    --bg: #0b0b0b;
+    --text: #e6e6e6;
+    --muted: #9aa0a6;
+    --border: #333333;
+    --chip-bg: rgba(255, 255, 255, 0.08);
+    --chip-text: #e6e6e6;
+    --spinner-border: #555555;
+    --spinner-top: #dddddd;
+    --silence-bg: #1a1a1a;
+    --loading-bg: rgba(255, 77, 77, 0.12);
+    --button-bg: #111111;
+    --button-border: #333333;
+    --wave-stroke: #e6e6e6;
+    --label-dia-text: #b3b3b3;
+    --label-trans-text: #ffffff;
+  }
+}
+
+:root[data-theme="dark"] {
+  --bg: #0b0b0b;
+  --text: #e6e6e6;
+  --muted: #9aa0a6;
+  --border: #333333;
+  --chip-bg: rgba(255, 255, 255, 0.08);
+  --chip-text: #e6e6e6;
+  --spinner-border: #555555;
+  --spinner-top: #dddddd;
+  --silence-bg: #1a1a1a;
+  --loading-bg: rgba(255, 77, 77, 0.12);
+  --button-bg: #111111;
+  --button-border: #333333;
+  --wave-stroke: #e6e6e6;
+  --label-dia-text: #b3b3b3;
+  --label-trans-text: #ffffff;
+}
+
+:root[data-theme="light"] {
+  --bg: #ffffff;
+  --text: #111111;
+  --muted: #666666;
+  --border: #e5e5e5;
+  --chip-bg: rgba(0, 0, 0, 0.04);
+  --chip-text: #000000;
+  --spinner-border: #8d8d8d5c;
+  --spinner-top: #b0b0b0;
+  --silence-bg: #f3f3f3;
+  --loading-bg: rgba(255, 77, 77, 0.06);
+  --button-bg: #ffffff;
+  --button-border: #e9e9e9;
+  --wave-stroke: #000000;
+  --label-dia-text: #868686;
+  --label-trans-text: #111111;
+}
+
+body {
+  font-family: ui-sans-serif, system-ui, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
+  margin: 20px;
+  text-align: center;
+  background-color: var(--bg);
+  color: var(--text);
+}
+
+/* Record button */
+#recordButton {
+  width: 50px;
+  height: 50px;
+  border: none;
+  border-radius: 50%;
+  background-color: var(--button-bg);
+  cursor: pointer;
+  transition: all 0.3s ease;
+  border: 1px solid var(--button-border);
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  position: relative;
+}
+
+#recordButton.recording {
+  width: 180px;
+  border-radius: 40px;
+  justify-content: flex-start;
+  padding-left: 20px;
+}
+
+#recordButton:active {
+  transform: scale(0.95);
+}
+
+.shape-container {
+  width: 25px;
+  height: 25px;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  flex-shrink: 0;
+}
+
+.shape {
+  width: 25px;
+  height: 25px;
+  background-color: rgb(209, 61, 53);
+  border-radius: 50%;
+  transition: all 0.3s ease;
+}
+
+#recordButton:disabled .shape {
+  background-color: #6e6d6d;
+}
+
+#recordButton.recording .shape {
+  border-radius: 5px;
+  width: 25px;
+  height: 25px;
+}
+
+/* Recording elements */
+.recording-info {
+  display: none;
+  align-items: center;
+  margin-left: 15px;
+  flex-grow: 1;
+}
+
+#recordButton.recording .recording-info {
+  display: flex;
+}
+
+.wave-container {
+  width: 60px;
+  height: 30px;
+  position: relative;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+#waveCanvas {
+  width: 100%;
+  height: 100%;
+}
+
+.timer {
+  font-size: 14px;
+  font-weight: 500;
+  color: var(--text);
+  margin-left: 10px;
+}
+
+#status {
+  margin-top: 20px;
+  font-size: 16px;
+  color: var(--text);
+}
+
+/* Settings */
+.settings-container {
+  display: flex;
+  justify-content: center;
+  align-items: center;
+  gap: 15px;
+  margin-top: 20px;
+}
+
+.settings {
+  display: flex;
+  flex-direction: column;
+  align-items: flex-start;
+  gap: 12px;
+}
+
+.field {
+  display: flex;
+  flex-direction: column;
+  align-items: flex-start;
+  gap: 3px;
+}
+
+#chunkSelector,
+#websocketInput,
+#themeSelector {
+  font-size: 16px;
+  padding: 5px 8px;
+  border-radius: 8px;
+  border: 1px solid var(--border);
+  background-color: var(--button-bg);
+  color: var(--text);
+  max-height: 34px;
+}
+
+#websocketInput {
+  width: 220px;
+}
+
+#chunkSelector:focus,
+#websocketInput:focus,
+#themeSelector:focus {
+  outline: none;
+  border-color: #007bff;
+  box-shadow: 0 0 0 3px rgba(0, 123, 255, 0.15);
+}
+
+label {
+  font-size: 13px;
+  color: var(--muted);
+}
+
+.ws-default {
+  font-size: 12px;
+  color: var(--muted);
+}
+
+/* Segmented pill control for Theme */
+.segmented {
+  display: inline-flex;
+  align-items: stretch;
+  border: 1px solid var(--button-border);
+  background-color: var(--button-bg);
+  border-radius: 999px;
+  overflow: hidden;
+}
+
+.segmented input[type="radio"] {
+  position: absolute;
+  opacity: 0;
+  pointer-events: none;
+}
+
+.theme-selector-container {
+  position: absolute;
+  top: 20px;
+  right: 20px;
+}
+
+.segmented label {
+  display: inline-flex;
+  align-items: center;
+  gap: 6px;
+  padding: 6px 12px;
+  font-size: 14px;
+  color: var(--muted);
+  cursor: pointer;
+  user-select: none;
+  transition: background-color 0.2s ease, color 0.2s ease;
+}
+
+.segmented label span {
+  display: none;
+}
+
+.segmented label:hover span {
+  display: inline;
+}
+
+.segmented label:hover {
+  background-color: var(--chip-bg);
+}
+
+.segmented img {
+  width: 16px;
+  height: 16px;
+}
+
+.segmented input[type="radio"]:checked + label {
+  background-color: var(--chip-bg);
+  color: var(--text);
+}
+
+.segmented input[type="radio"]:focus-visible + label,
+.segmented input[type="radio"]:focus + label {
+  outline: 2px solid #007bff;
+  outline-offset: 2px;
+  border-radius: 999px;
+}
+
+/* Transcript area */
+#linesTranscript {
+  margin: 20px auto;
+  max-width: 700px;
+  text-align: left;
+  font-size: 16px;
+}
+
+#linesTranscript p {
+  margin: 0px 0;
+}
+
+#linesTranscript strong {
+  color: var(--text);
+}
+
+#speaker {
+  border: 1px solid var(--border);
+  border-radius: 100px;
+  padding: 2px 10px;
+  font-size: 14px;
+  margin-bottom: 0px;
+}
+
+.label_diarization {
+  background-color: var(--chip-bg);
+  border-radius: 8px 8px 8px 8px;
+  padding: 2px 10px;
+  margin-left: 10px;
+  display: inline-block;
+  white-space: nowrap;
+  font-size: 14px;
+  margin-bottom: 0px;
+  color: var(--label-dia-text);
+}
+
+.label_transcription {
+  background-color: var(--chip-bg);
+  border-radius: 8px 8px 8px 8px;
+  padding: 2px 10px;
+  display: inline-block;
+  white-space: nowrap;
+  margin-left: 10px;
+  font-size: 14px;
+  margin-bottom: 0px;
+  color: var(--label-trans-text);
+}
+
+#timeInfo {
+  color: var(--muted);
+  margin-left: 10px;
+}
+
+.textcontent {
+  font-size: 16px;
+  padding-left: 10px;
+  margin-bottom: 10px;
+  margin-top: 1px;
+  padding-top: 5px;
+  border-radius: 0px 0px 0px 10px;
+}
+
+.buffer_diarization {
+  color: var(--label-dia-text);
+  margin-left: 4px;
+}
+
+.buffer_transcription {
+  color: #7474748c;
+  margin-left: 4px;
+}
+
+.spinner {
+  display: inline-block;
+  width: 8px;
+  height: 8px;
+  border: 2px solid var(--spinner-border);
+  border-top: 2px solid var(--spinner-top);
+  border-radius: 50%;
+  animation: spin 0.7s linear infinite;
+  vertical-align: middle;
+  margin-bottom: 2px;
+  margin-right: 5px;
+}
+
+@keyframes spin {
+  to {
+    transform: rotate(360deg);
+  }
+}
+
+.silence {
+  color: var(--muted);
+  background-color: var(--silence-bg);
+  font-size: 13px;
+  border-radius: 30px;
+  padding: 2px 10px;
+}
+
+.loading {
+  color: var(--muted);
+  background-color: var(--loading-bg);
+  border-radius: 8px 8px 8px 0px;
+  padding: 2px 10px;
+  font-size: 14px;
+  margin-bottom: 0px;
+}

whisperlivekit/web/live_transcription.html

@@ -1,682 +1,61 @@
 <!DOCTYPE html>
 <html lang="en">
-
 <head>
-    <meta charset="UTF-8" />
-    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-    <title>Audio Transcription</title>
-    <style>
-        body {
-            font-family: ui-sans-serif, system-ui, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
-            margin: 20px;
-            text-align: center;
-        }
-
-        #recordButton {
-            width: 50px;
-            height: 50px;
-            border: none;
-            border-radius: 50%;
-            background-color: white;
-            cursor: pointer;
-            transition: all 0.3s ease;
-            border: 1px solid rgb(233, 233, 233);
-            display: flex;
-            align-items: center;
-            justify-content: center;
-            position: relative;
-        }
-
-        #recordButton.recording {
-            width: 180px;
-            border-radius: 40px;
-            justify-content: flex-start;
-            padding-left: 20px;
-        }
-
-        #recordButton:active {
-            transform: scale(0.95);
-        }
-
-        .shape-container {
-            width: 25px;
-            height: 25px;
-            display: flex;
-            align-items: center;
-            justify-content: center;
-            flex-shrink: 0;
-        }
-
-        .shape {
-            width: 25px;
-            height: 25px;
-            background-color: rgb(209, 61, 53);
-            border-radius: 50%;
-            transition: all 0.3s ease;
-        }
-
-        #recordButton:disabled .shape {
-            background-color: #6e6d6d;
-        }
-
-        #recordButton.recording .shape {
-            border-radius: 5px;
-            width: 25px;
-            height: 25px;
-        }
-
-        /* Recording elements */
-        .recording-info {
-            display: none;
-            align-items: center;
-            margin-left: 15px;
-            flex-grow: 1;
-        }
-
-        #recordButton.recording .recording-info {
-            display: flex;
-        }
-
-        .wave-container {
-            width: 60px;
-            height: 30px;
-            position: relative;
-            display: flex;
-            align-items: center;
-            justify-content: center;
-        }
-
-        #waveCanvas {
-            width: 100%;
-            height: 100%;
-        }
-
-        .timer {
-            font-size: 14px;
-            font-weight: 500;
-            color: #333;
-            margin-left: 10px;
-        }
-
-        #status {
-            margin-top: 20px;
-            font-size: 16px;
-            color: #333;
-        }
-
-        .settings-container {
-            display: flex;
-            justify-content: center;
-            align-items: center;
-            gap: 15px;
-            margin-top: 20px;
-        }
-
-        .settings {
-            display: flex;
-            flex-direction: column;
-            align-items: flex-start;
-            gap: 5px;
-        }
-
-        #chunkSelector,
-        #websocketInput {
-            font-size: 16px;
-            padding: 5px;
-            border-radius: 5px;
-            border: 1px solid #ddd;
-            background-color: #ffffff;
-            max-height: 30px;
-        }
-
-        #websocketInput {
-            width: 200px;
-        }
-
-        #chunkSelector:focus,
-        #websocketInput:focus {
-            outline: none;
-            border-color: #007bff;
-        }
-
-        label {
-            font-size: 14px;
-        }
-
-        /* Speaker-labeled transcript area */
-        #linesTranscript {
-            margin: 20px auto;
-            max-width: 700px;
-            text-align: left;
-            font-size: 16px;
-        }
-
-        #linesTranscript p {
-            margin: 0px 0;
-        }
-
-        #linesTranscript strong {
-            color: #333;
-        }
-
-        #speaker {
-            border: 1px solid rgb(229, 229, 229);
-            border-radius: 100px;
-            padding: 2px 10px;
-            font-size: 14px;
-            margin-bottom: 0px;
-        }
-        .label_diarization {
-            background-color: #ffffff66;
-            border-radius: 8px 8px 8px 8px;
-            padding: 2px 10px;
-            margin-left: 10px;
-            display: inline-block;
-            white-space: nowrap;
-            font-size: 14px;
-            margin-bottom: 0px;
-            color: rgb(134, 134, 134)
-        }
-
-        .label_transcription {
-            background-color: #ffffff66;
-            border-radius: 8px 8px 8px 8px;
-            padding: 2px 10px;
-            display: inline-block;
-            white-space: nowrap;
-            margin-left: 10px;
-            font-size: 14px;
-            margin-bottom: 0px;
-            color: #000000
-        }
-
-        #timeInfo {
-            color: #666;
-            margin-left: 10px;
-        }
-
-        .textcontent {
-            font-size: 16px;
-            /* margin-left: 10px; */
-            padding-left: 10px;
-            margin-bottom: 10px;
-            margin-top: 1px;
-            padding-top: 5px;
-            border-radius: 0px 0px 0px 10px;
-        }
-
-        .buffer_diarization {
-            color: rgb(134, 134, 134);
-            margin-left: 4px;
-        }
-
-        .buffer_transcription {
-            color: #7474748c;
-            margin-left: 4px;
-        }
-
-
-        .spinner {
-            display: inline-block;
-            width: 8px;
-            height: 8px;
-            border: 2px solid #8d8d8d5c;
-            border-top: 2px solid #6c6c6ce5;
-            border-radius: 50%;
-            animation: spin 0.6s linear infinite;
-            vertical-align: middle;
-            margin-bottom: 2px;
-            margin-right: 5px;
-        }
-
-        @keyframes spin {
-            to {
-                transform: rotate(360deg);
-            }
-        }
-
-        .silence {
-            color: #666;
-            background-color: #f3f3f3;
-            font-size: 13px;
-            border-radius: 30px;
-            padding: 2px 10px;
-        }
-
-        .loading {
-            color: #666;
-            background-color: #ff4d4d0f;
-            border-radius: 8px 8px 8px 0px;
-            padding: 2px 10px;
-            font-size: 14px;
-            margin-bottom: 0px;
-        }
-    </style>
+  <meta charset="UTF-8" />
+  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+  <title>WhisperLiveKit</title>
+  <link rel="stylesheet" href="/web/live_transcription.css" />
 </head>
-
 <body>
-
-    <div class="settings-container">
-        <button id="recordButton">
-            <div class="shape-container">
-                <div class="shape"></div>
-            </div>
-            <div class="recording-info">
-                <div class="wave-container">
-                    <canvas id="waveCanvas"></canvas>
-                </div>
-                <div class="timer">00:00</div>
-            </div>
-        </button>
-        <div class="settings">
-            <div>
-                <label for="chunkSelector">Chunk size (ms):</label>
-                <select id="chunkSelector">
-                    <option value="500">500 ms</option>
-                    <option value="1000" selected>1000 ms</option>
-                    <option value="2000">2000 ms</option>
-                    <option value="3000">3000 ms</option>
-                    <option value="4000">4000 ms</option>
-                    <option value="5000">5000 ms</option>
-                </select>
-            </div>
-            <div>
-                <label for="websocketInput">WebSocket URL:</label>
-                <input id="websocketInput" type="text" />
-            </div>
+  <div class="settings-container">
+    <button id="recordButton">
+      <div class="shape-container">
+        <div class="shape"></div>
+      </div>
+      <div class="recording-info">
+        <div class="wave-container">
+          <canvas id="waveCanvas"></canvas>
         </div>
+        <div class="timer">00:00</div>
+      </div>
+    </button>
+
+    <div class="settings">
+      <div class="field">
+        <label for="websocketInput">WebSocket URL</label>
+        <input id="websocketInput" type="text" placeholder="ws://host:port/asr" />
+      </div>
+
+      </div>
     </div>
+  </div>
 
-    <p id="status"></p>
+  <div class="theme-selector-container">
+    <div class="segmented" role="radiogroup" aria-label="Theme selector">
+      <input type="radio" id="theme-system" name="theme" value="system" />
+      <label for="theme-system" title="System">
+        <img src="/web/src/system_mode.svg" alt="" />
+        <span>System</span>
+      </label>
 
-    <!-- Speaker-labeled transcript -->
-    <div id="linesTranscript"></div>
+      <input type="radio" id="theme-light" name="theme" value="light" />
+      <label for="theme-light" title="Light">
+        <img src="/web/src/light_mode.svg" alt="" />
+        <span>Light</span>
+      </label>
 
-    <script>
-        let isRecording = false;
-        let websocket = null;
-        let recorder = null;
-        let chunkDuration = 1000;
-        let websocketUrl = "ws://localhost:8000/asr";
-        let userClosing = false;
-        let startTime = null;
-        let timerInterval = null;
-        let audioContext = null;
-        let analyser = null;
-        let microphone = null;
-        let waveCanvas = document.getElementById("waveCanvas");
-        let waveCtx = waveCanvas.getContext("2d");
-        let animationFrame = null;
-        let waitingForStop = false;
-        let lastReceivedData = null;
-        waveCanvas.width = 60 * (window.devicePixelRatio || 1);
-        waveCanvas.height = 30 * (window.devicePixelRatio || 1);
-        waveCtx.scale(window.devicePixelRatio || 1, window.devicePixelRatio || 1);
+      <input type="radio" id="theme-dark" name="theme" value="dark" />
+      <label for="theme-dark" title="Dark">
+        <img src="/web/src/dark_mode.svg" alt="" />
+        <span>Dark</span>
+      </label>
+    </div>
+  </div>
 
-        const statusText = document.getElementById("status");
-        const recordButton = document.getElementById("recordButton");
-        const chunkSelector = document.getElementById("chunkSelector");
-        const websocketInput = document.getElementById("websocketInput");
-        const linesTranscriptDiv = document.getElementById("linesTranscript");
-        const timerElement = document.querySelector(".timer");
+  <p id="status"></p>
 
-        const host = window.location.hostname || "localhost";
-        const port = window.location.port;
-        const protocol = window.location.protocol === "https:" ? "wss" : "ws";
-        const defaultWebSocketUrl = `${protocol}://${host}:${port}/asr`;
-        websocketInput.value = defaultWebSocketUrl;
-        websocketUrl = defaultWebSocketUrl;
+  <div id="linesTranscript"></div>
 
-        chunkSelector.addEventListener("change", () => {
-            chunkDuration = parseInt(chunkSelector.value);
-        });
-
-        websocketInput.addEventListener("change", () => {
-            const urlValue = websocketInput.value.trim();
-            if (!urlValue.startsWith("ws://") && !urlValue.startsWith("wss://")) {
-                statusText.textContent = "Invalid WebSocket URL (must start with ws:// or wss://)";
-                return;
-            }
-            websocketUrl = urlValue;
-            statusText.textContent = "WebSocket URL updated. Ready to connect.";
-        });
-
-        function setupWebSocket() {
-            return new Promise((resolve, reject) => {
-                try {
-                    websocket = new WebSocket(websocketUrl);
-                } catch (error) {
-                    statusText.textContent = "Invalid WebSocket URL. Please check and try again.";
-                    reject(error);
-                    return;
-                }
-
-                websocket.onopen = () => {
-                    statusText.textContent = "Connected to server.";
-                    resolve();
-                };
-
-                websocket.onclose = () => {
-                    if (userClosing) {
-                        if (waitingForStop) {
-                            statusText.textContent = "Processing finalized or connection closed.";
-                            if (lastReceivedData) {
-                                renderLinesWithBuffer(
-                                    lastReceivedData.lines || [],
-                                    lastReceivedData.buffer_diarization || "",
-                                    lastReceivedData.buffer_transcription || "",
-                                    0, 0, true // isFinalizing = true
-                                );
-                            }
-                        }
-                        // If ready_to_stop was received, statusText is already "Finished processing..."
-                        // and waitingForStop is false.
-                    } else {
-                        statusText.textContent = "Disconnected from the WebSocket server. (Check logs if model is loading.)";
-                        if (isRecording) {
-                            stopRecording(); 
-                        }
-                    }
-                    isRecording = false;  
-                    waitingForStop = false; 
-                    userClosing = false;  
-                    lastReceivedData = null;  
-                    websocket = null;    
-                    updateUI();  
-                };
-
-                websocket.onerror = () => {
-                    statusText.textContent = "Error connecting to WebSocket.";
-                    reject(new Error("Error connecting to WebSocket"));
-                };
-
-                // Handle messages from server
-                websocket.onmessage = (event) => {
-                    const data = JSON.parse(event.data);
-                    
-                    // Check for status messages
-                    if (data.type === "ready_to_stop") {
-                        console.log("Ready to stop received, finalizing display and closing WebSocket.");
-                        waitingForStop = false;
-
-                        if (lastReceivedData) {
-                            renderLinesWithBuffer(
-                                lastReceivedData.lines || [],
-                                lastReceivedData.buffer_diarization || "",
-                                lastReceivedData.buffer_transcription || "",
-                                0, // No more lag
-                                0, // No more lag
-                                true // isFinalizing = true
-                            );
-                        }
-                        statusText.textContent = "Finished processing audio! Ready to record again.";
-                        recordButton.disabled = false;
-                        
-                        if (websocket) {
-                            websocket.close(); // will trigger onclose
-                            // websocket = null; // onclose handle setting websocket to null
-                        }
-                        return;
-                    }
-                    
-                    lastReceivedData = data; 
-                    
-                    // Handle normal transcription updates
-                    const { 
-                        lines = [], 
-                        buffer_transcription = "", 
-                        buffer_diarization = "",
-                        remaining_time_transcription = 0,
-                        remaining_time_diarization = 0,
-                        status = "active_transcription"
-                    } = data;
-                    
-                    renderLinesWithBuffer(
-                        lines, 
-                        buffer_diarization, 
-                        buffer_transcription, 
-                        remaining_time_diarization,
-                        remaining_time_transcription,
-                        false,
-                        status
-                    );
-                };
-            });
-        }
-
-        function renderLinesWithBuffer(lines, buffer_diarization, buffer_transcription, remaining_time_diarization, remaining_time_transcription, isFinalizing = false, current_status = "active_transcription") {
-            if (current_status === "no_audio_detected") {
-                linesTranscriptDiv.innerHTML = "<p style='text-align: center; color: #666; margin-top: 20px;'><em>No audio detected...</em></p>";
-                return; 
-            }
-
-            const linesHtml = lines.map((item, idx) => {
-                let timeInfo = "";
-                if (item.beg !== undefined && item.end !== undefined) {
-                    timeInfo = ` ${item.beg} - ${item.end}`;
-                }
-
-                let speakerLabel = "";
-                if (item.speaker === -2) {
-                    speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`;
-                } else if (item.speaker == 0 && !isFinalizing) {
-                    speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'>${remaining_time_diarization} second(s) of audio are undergoing diarization</span></span>`;
-                } else if (item.speaker == -1) {
-                    speakerLabel = `<span id="speaker">Speaker 1<span id='timeInfo'>${timeInfo}</span></span>`;
-                } else if (item.speaker !== -1 && item.speaker !== 0) {
-                    speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
-                }
-
-
-                let currentLineText = item.text || "";
-
-                if (idx === lines.length - 1) { 
-                    if (!isFinalizing) {
-                        if (remaining_time_transcription > 0) {
-                             speakerLabel += `<span class="label_transcription"><span class="spinner"></span>Transcription lag <span id='timeInfo'>${remaining_time_transcription}s</span></span>`;
-                        }
-                        if (buffer_diarization && remaining_time_diarization > 0) {
-                             speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Diarization lag<span id='timeInfo'>${remaining_time_diarization}s</span></span>`;
-                        }
-                    }
-
-                    if (buffer_diarization) {
-                        if (isFinalizing) {
-                            currentLineText += (currentLineText.length > 0 && buffer_diarization.trim().length > 0 ? " " : "") + buffer_diarization.trim();
-                        } else {
-                            currentLineText += `<span class="buffer_diarization">${buffer_diarization}</span>`;
-                        }
-                    }
-                    if (buffer_transcription) {
-                        if (isFinalizing) {
-                            currentLineText += (currentLineText.length > 0 && buffer_transcription.trim().length > 0 ? " " : "") + buffer_transcription.trim();
-                        } else {
-                            currentLineText += `<span class="buffer_transcription">${buffer_transcription}</span>`;
-                        }
-                    }
-                }
-                
-                return currentLineText.trim().length > 0 || speakerLabel.length > 0
-                    ? `<p>${speakerLabel}<br/><div class='textcontent'>${currentLineText}</div></p>`
-                    : `<p>${speakerLabel}<br/></p>`; 
-            }).join("");
-
-            linesTranscriptDiv.innerHTML = linesHtml;
-        }
-
-        function updateTimer() {
-            if (!startTime) return;
-            
-            const elapsed = Math.floor((Date.now() - startTime) / 1000);
-            const minutes = Math.floor(elapsed / 60).toString().padStart(2, "0");
-            const seconds = (elapsed % 60).toString().padStart(2, "0");
-            timerElement.textContent = `${minutes}:${seconds}`;
-        }
-
-        function drawWaveform() {
-            if (!analyser) return;
-            
-            const bufferLength = analyser.frequencyBinCount;
-            const dataArray = new Uint8Array(bufferLength);
-            analyser.getByteTimeDomainData(dataArray);
-            
-            waveCtx.clearRect(0, 0, waveCanvas.width / (window.devicePixelRatio || 1), waveCanvas.height / (window.devicePixelRatio || 1));
-            waveCtx.lineWidth = 1;
-            waveCtx.strokeStyle = 'rgb(0, 0, 0)';
-            waveCtx.beginPath();
-            
-            const sliceWidth = (waveCanvas.width / (window.devicePixelRatio || 1)) / bufferLength;
-            let x = 0;
-            
-            for (let i = 0; i < bufferLength; i++) {
-                const v = dataArray[i] / 128.0;
-                const y = v * (waveCanvas.height / (window.devicePixelRatio || 1)) / 2;
-                
-                if (i === 0) {
-                    waveCtx.moveTo(x, y);
-                } else {
-                    waveCtx.lineTo(x, y);
-                }
-                
-                x += sliceWidth;
-            }
-            
-            waveCtx.lineTo(waveCanvas.width / (window.devicePixelRatio || 1), waveCanvas.height / (window.devicePixelRatio || 1) / 2);
-            waveCtx.stroke();
-            
-            animationFrame = requestAnimationFrame(drawWaveform);
-        }
-
-        async function startRecording() {
-            try {
-                const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
-                
-                audioContext = new (window.AudioContext || window.webkitAudioContext)();
-                analyser = audioContext.createAnalyser();
-                analyser.fftSize = 256;
-                microphone = audioContext.createMediaStreamSource(stream);
-                microphone.connect(analyser);
-                
-                recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
-                recorder.ondataavailable = (e) => {
-                    if (websocket && websocket.readyState === WebSocket.OPEN) {
-                        websocket.send(e.data);
-                    }
-                };
-                recorder.start(chunkDuration);
-                
-                startTime = Date.now();
-                timerInterval = setInterval(updateTimer, 1000);
-                drawWaveform();
-                
-                isRecording = true;
-                updateUI();
-            } catch (err) {
-                statusText.textContent = "Error accessing microphone. Please allow microphone access.";
-                console.error(err);
-            }
-        }
-
-        async function stopRecording() {
-            userClosing = true;
-            waitingForStop = true;
-            
-            if (websocket && websocket.readyState === WebSocket.OPEN) {
-                // Send empty audio buffer as stop signal
-                const emptyBlob = new Blob([], { type: 'audio/webm' });
-                websocket.send(emptyBlob);
-                statusText.textContent = "Recording stopped. Processing final audio...";
-            }
-            
-            if (recorder) {
-                recorder.stop();
-                recorder = null;
-            }
-            
-            if (microphone) {
-                microphone.disconnect();
-                microphone = null;
-            }
-            
-            if (analyser) {
-                analyser = null;
-            }
-            
-            if (audioContext && audioContext.state !== 'closed') {
-                try {
-                    audioContext.close();
-                } catch (e) {
-                    console.warn("Could not close audio context:", e);
-                }
-                audioContext = null;
-            }
-            
-            if (animationFrame) {
-                cancelAnimationFrame(animationFrame);
-                animationFrame = null;
-            }
-            
-            if (timerInterval) {
-                clearInterval(timerInterval);
-                timerInterval = null;
-            }            
-            timerElement.textContent = "00:00";
-            startTime = null;
-            
-            
-            isRecording = false;
-            updateUI();	
-        }
-
-        async function toggleRecording() {
-            if (!isRecording) {
-                if (waitingForStop) {
-                    console.log("Waiting for stop, early return");
-                    return;  // Early return, UI is already updated
-                }
-                console.log("Connecting to WebSocket");
-                try {
-                    // If we have an active WebSocket that's still processing, just restart audio capture
-                    if (websocket && websocket.readyState === WebSocket.OPEN) {
-                        await startRecording();
-                    } else {
-                        // If no active WebSocket or it's closed, create new one
-                        await setupWebSocket();
-                        await startRecording();
-                    }
-                } catch (err) {
-                    statusText.textContent = "Could not connect to WebSocket or access mic. Aborted.";
-                    console.error(err);
-                }
-            } else {
-                console.log("Stopping recording");
-                stopRecording();
-            }
-        }
-
-        function updateUI() {
-            recordButton.classList.toggle("recording", isRecording);
-            recordButton.disabled = waitingForStop;
-
-            if (waitingForStop) {
-                if (statusText.textContent !== "Recording stopped. Processing final audio...") {
-                     statusText.textContent = "Please wait for processing to complete...";
-                }
-            } else if (isRecording) {
-                statusText.textContent = "Recording...";
-            } else {
-                if (statusText.textContent !== "Finished processing audio! Ready to record again." &&
-                    statusText.textContent !== "Processing finalized or connection closed.") {
-                    statusText.textContent = "Click to start transcription";
-                }
-            }
-            if (!waitingForStop) {
-                recordButton.disabled = false;
-            }
-        }
-
-        recordButton.addEventListener("click", toggleRecording);
-    </script>
+  <script src="/web/live_transcription.js"></script>
 </body>
-
 </html>

whisperlivekit/web/live_transcription.js

@@ -0,0 +1,518 @@
+/* Theme, WebSocket, recording, rendering logic extracted from inline script and adapted for segmented theme control and WS caption */
+
+let isRecording = false;
+let websocket = null;
+let recorder = null;
+let chunkDuration = 100;
+let websocketUrl = "ws://localhost:8000/asr";
+let userClosing = false;
+let wakeLock = null;
+let startTime = null;
+let timerInterval = null;
+let audioContext = null;
+let analyser = null;
+let microphone = null;
+let waveCanvas = document.getElementById("waveCanvas");
+let waveCtx = waveCanvas.getContext("2d");
+let animationFrame = null;
+let waitingForStop = false;
+let lastReceivedData = null;
+let lastSignature = null;
+
+waveCanvas.width = 60 * (window.devicePixelRatio || 1);
+waveCanvas.height = 30 * (window.devicePixelRatio || 1);
+waveCtx.scale(window.devicePixelRatio || 1, window.devicePixelRatio || 1);
+
+const statusText = document.getElementById("status");
+const recordButton = document.getElementById("recordButton");
+const chunkSelector = document.getElementById("chunkSelector");
+const websocketInput = document.getElementById("websocketInput");
+const websocketDefaultSpan = document.getElementById("wsDefaultUrl");
+const linesTranscriptDiv = document.getElementById("linesTranscript");
+const timerElement = document.querySelector(".timer");
+const themeRadios = document.querySelectorAll('input[name="theme"]');
+
+function getWaveStroke() {
+  const styles = getComputedStyle(document.documentElement);
+  const v = styles.getPropertyValue("--wave-stroke").trim();
+  return v || "#000";
+}
+
+let waveStroke = getWaveStroke();
+function updateWaveStroke() {
+  waveStroke = getWaveStroke();
+}
+
+function applyTheme(pref) {
+  if (pref === "light") {
+    document.documentElement.setAttribute("data-theme", "light");
+  } else if (pref === "dark") {
+    document.documentElement.setAttribute("data-theme", "dark");
+  } else {
+    document.documentElement.removeAttribute("data-theme");
+  }
+  updateWaveStroke();
+}
+
+// Persisted theme preference
+const savedThemePref = localStorage.getItem("themePreference") || "system";
+applyTheme(savedThemePref);
+if (themeRadios.length) {
+  themeRadios.forEach((r) => {
+    r.checked = r.value === savedThemePref;
+    r.addEventListener("change", () => {
+      if (r.checked) {
+        localStorage.setItem("themePreference", r.value);
+        applyTheme(r.value);
+      }
+    });
+  });
+}
+
+// React to OS theme changes when in "system" mode
+const darkMq = window.matchMedia && window.matchMedia("(prefers-color-scheme: dark)");
+const handleOsThemeChange = () => {
+  const pref = localStorage.getItem("themePreference") || "system";
+  if (pref === "system") updateWaveStroke();
+};
+if (darkMq && darkMq.addEventListener) {
+  darkMq.addEventListener("change", handleOsThemeChange);
+} else if (darkMq && darkMq.addListener) {
+  // deprecated, but included for Safari compatibility
+  darkMq.addListener(handleOsThemeChange);
+}
+
+// Helpers
+function fmt1(x) {
+  const n = Number(x);
+  return Number.isFinite(n) ? n.toFixed(1) : x;
+}
+
+// Default WebSocket URL computation
+const host = window.location.hostname || "localhost";
+const port = window.location.port;
+const protocol = window.location.protocol === "https:" ? "wss" : "ws";
+const defaultWebSocketUrl = `${protocol}://${host}${port ? ":" + port : ""}/asr`;
+
+// Populate default caption and input
+if (websocketDefaultSpan) websocketDefaultSpan.textContent = defaultWebSocketUrl;
+websocketInput.value = defaultWebSocketUrl;
+websocketUrl = defaultWebSocketUrl;
+
+// Optional chunk selector (guard for presence)
+if (chunkSelector) {
+  chunkSelector.addEventListener("change", () => {
+    chunkDuration = parseInt(chunkSelector.value);
+  });
+}
+
+// WebSocket input change handling
+websocketInput.addEventListener("change", () => {
+  const urlValue = websocketInput.value.trim();
+  if (!urlValue.startsWith("ws://") && !urlValue.startsWith("wss://")) {
+    statusText.textContent = "Invalid WebSocket URL (must start with ws:// or wss://)";
+    return;
+  }
+  websocketUrl = urlValue;
+  statusText.textContent = "WebSocket URL updated. Ready to connect.";
+});
+
+function setupWebSocket() {
+  return new Promise((resolve, reject) => {
+    try {
+      websocket = new WebSocket(websocketUrl);
+    } catch (error) {
+      statusText.textContent = "Invalid WebSocket URL. Please check and try again.";
+      reject(error);
+      return;
+    }
+
+    websocket.onopen = () => {
+      statusText.textContent = "Connected to server.";
+      resolve();
+    };
+
+    websocket.onclose = () => {
+      if (userClosing) {
+        if (waitingForStop) {
+          statusText.textContent = "Processing finalized or connection closed.";
+          if (lastReceivedData) {
+            renderLinesWithBuffer(
+              lastReceivedData.lines || [],
+              lastReceivedData.buffer_diarization || "",
+              lastReceivedData.buffer_transcription || "",
+              0,
+              0,
+              true
+            );
+          }
+        }
+      } else {
+        statusText.textContent = "Disconnected from the WebSocket server. (Check logs if model is loading.)";
+        if (isRecording) {
+          stopRecording();
+        }
+      }
+      isRecording = false;
+      waitingForStop = false;
+      userClosing = false;
+      lastReceivedData = null;
+      websocket = null;
+      updateUI();
+    };
+
+    websocket.onerror = () => {
+      statusText.textContent = "Error connecting to WebSocket.";
+      reject(new Error("Error connecting to WebSocket"));
+    };
+
+    websocket.onmessage = (event) => {
+      const data = JSON.parse(event.data);
+
+      if (data.type === "ready_to_stop") {
+        console.log("Ready to stop received, finalizing display and closing WebSocket.");
+        waitingForStop = false;
+
+        if (lastReceivedData) {
+          renderLinesWithBuffer(
+            lastReceivedData.lines || [],
+            lastReceivedData.buffer_diarization || "",
+            lastReceivedData.buffer_transcription || "",
+            0,
+            0,
+            true
+          );
+        }
+        statusText.textContent = "Finished processing audio! Ready to record again.";
+        recordButton.disabled = false;
+
+        if (websocket) {
+          websocket.close();
+        }
+        return;
+      }
+
+      lastReceivedData = data;
+
+      const {
+        lines = [],
+        buffer_transcription = "",
+        buffer_diarization = "",
+        remaining_time_transcription = 0,
+        remaining_time_diarization = 0,
+        status = "active_transcription",
+      } = data;
+
+      renderLinesWithBuffer(
+        lines,
+        buffer_diarization,
+        buffer_transcription,
+        remaining_time_diarization,
+        remaining_time_transcription,
+        false,
+        status
+      );
+    };
+  });
+}
+
+function renderLinesWithBuffer(
+  lines,
+  buffer_diarization,
+  buffer_transcription,
+  remaining_time_diarization,
+  remaining_time_transcription,
+  isFinalizing = false,
+  current_status = "active_transcription"
+) {
+  if (current_status === "no_audio_detected") {
+    linesTranscriptDiv.innerHTML =
+      "<p style='text-align: center; color: var(--muted); margin-top: 20px;'><em>No audio detected...</em></p>";
+    return;
+  }
+
+  const showLoading = !isFinalizing && (lines || []).some((it) => it.speaker == 0);
+  const showTransLag = !isFinalizing && remaining_time_transcription > 0;
+  const showDiaLag = !isFinalizing && !!buffer_diarization && remaining_time_diarization > 0;
+  const signature = JSON.stringify({
+    lines: (lines || []).map((it) => ({ speaker: it.speaker, text: it.text, beg: it.beg, end: it.end })),
+    buffer_transcription: buffer_transcription || "",
+    buffer_diarization: buffer_diarization || "",
+    status: current_status,
+    showLoading,
+    showTransLag,
+    showDiaLag,
+    isFinalizing: !!isFinalizing,
+  });
+  if (lastSignature === signature) {
+    const t = document.querySelector(".lag-transcription-value");
+    if (t) t.textContent = fmt1(remaining_time_transcription);
+    const d = document.querySelector(".lag-diarization-value");
+    if (d) d.textContent = fmt1(remaining_time_diarization);
+    const ld = document.querySelector(".loading-diarization-value");
+    if (ld) ld.textContent = fmt1(remaining_time_diarization);
+    return;
+  }
+  lastSignature = signature;
+
+  const linesHtml = (lines || [])
+    .map((item, idx) => {
+      let timeInfo = "";
+      if (item.beg !== undefined && item.end !== undefined) {
+        timeInfo = ` ${item.beg} - ${item.end}`;
+      }
+
+      let speakerLabel = "";
+      if (item.speaker === -2) {
+        speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`;
+      } else if (item.speaker == 0 && !isFinalizing) {
+        speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'><span class="loading-diarization-value">${fmt1(
+          remaining_time_diarization
+        )}</span> second(s) of audio are undergoing diarization</span></span>`;
+      } else if (item.speaker !== 0) {
+        speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
+      }
+
+      let currentLineText = item.text || "";
+
+      if (idx === lines.length - 1) {
+        if (!isFinalizing && item.speaker !== -2) {
+          if (remaining_time_transcription > 0) {
+            speakerLabel += `<span class="label_transcription"><span class="spinner"></span>Transcription lag <span id='timeInfo'><span class="lag-transcription-value">${fmt1(
+              remaining_time_transcription
+            )}</span>s</span></span>`;
+          }
+          if (buffer_diarization && remaining_time_diarization > 0) {
+            speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Diarization lag<span id='timeInfo'><span class="lag-diarization-value">${fmt1(
+              remaining_time_diarization
+            )}</span>s</span></span>`;
+          }
+        }
+
+        if (buffer_diarization) {
+          if (isFinalizing) {
+            currentLineText +=
+              (currentLineText.length > 0 && buffer_diarization.trim().length > 0 ? " " : "") + buffer_diarization.trim();
+          } else {
+            currentLineText += `<span class="buffer_diarization">${buffer_diarization}</span>`;
+          }
+        }
+        if (buffer_transcription) {
+          if (isFinalizing) {
+            currentLineText +=
+              (currentLineText.length > 0 && buffer_transcription.trim().length > 0 ? " " : "") +
+              buffer_transcription.trim();
+          } else {
+            currentLineText += `<span class="buffer_transcription">${buffer_transcription}</span>`;
+          }
+        }
+      }
+
+      return currentLineText.trim().length > 0 || speakerLabel.length > 0
+        ? `<p>${speakerLabel}<br/><div class='textcontent'>${currentLineText}</div></p>`
+        : `<p>${speakerLabel}<br/></p>`;
+    })
+    .join("");
+
+  linesTranscriptDiv.innerHTML = linesHtml;
+  window.scrollTo({ top: document.body.scrollHeight, behavior: "smooth" });
+}
+
+function updateTimer() {
+  if (!startTime) return;
+
+  const elapsed = Math.floor((Date.now() - startTime) / 1000);
+  const minutes = Math.floor(elapsed / 60).toString().padStart(2, "0");
+  const seconds = (elapsed % 60).toString().padStart(2, "0");
+  timerElement.textContent = `${minutes}:${seconds}`;
+}
+
+function drawWaveform() {
+  if (!analyser) return;
+
+  const bufferLength = analyser.frequencyBinCount;
+  const dataArray = new Uint8Array(bufferLength);
+  analyser.getByteTimeDomainData(dataArray);
+
+  waveCtx.clearRect(
+    0,
+    0,
+    waveCanvas.width / (window.devicePixelRatio || 1),
+    waveCanvas.height / (window.devicePixelRatio || 1)
+  );
+  waveCtx.lineWidth = 1;
+  waveCtx.strokeStyle = waveStroke;
+  waveCtx.beginPath();
+
+  const sliceWidth = (waveCanvas.width / (window.devicePixelRatio || 1)) / bufferLength;
+  let x = 0;
+
+  for (let i = 0; i < bufferLength; i++) {
+    const v = dataArray[i] / 128.0;
+    const y = (v * (waveCanvas.height / (window.devicePixelRatio || 1))) / 2;
+
+    if (i === 0) {
+      waveCtx.moveTo(x, y);
+    } else {
+      waveCtx.lineTo(x, y);
+    }
+
+    x += sliceWidth;
+  }
+
+  waveCtx.lineTo(
+    waveCanvas.width / (window.devicePixelRatio || 1),
+    (waveCanvas.height / (window.devicePixelRatio || 1)) / 2
+  );
+  waveCtx.stroke();
+
+  animationFrame = requestAnimationFrame(drawWaveform);
+}
+
+async function startRecording() {
+  try {
+    try {
+      wakeLock = await navigator.wakeLock.request("screen");
+    } catch (err) {
+      console.log("Error acquiring wake lock.");
+    }
+
+    const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+
+    audioContext = new (window.AudioContext || window.webkitAudioContext)();
+    analyser = audioContext.createAnalyser();
+    analyser.fftSize = 256;
+    microphone = audioContext.createMediaStreamSource(stream);
+    microphone.connect(analyser);
+
+    recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
+    recorder.ondataavailable = (e) => {
+      if (websocket && websocket.readyState === WebSocket.OPEN) {
+        websocket.send(e.data);
+      }
+    };
+    recorder.start(chunkDuration);
+
+    startTime = Date.now();
+    timerInterval = setInterval(updateTimer, 1000);
+    drawWaveform();
+
+    isRecording = true;
+    updateUI();
+  } catch (err) {
+    if (window.location.hostname === "0.0.0.0") {
+      statusText.textContent =
+        "Error accessing microphone. Browsers may block microphone access on 0.0.0.0. Try using localhost:8000 instead.";
+    } else {
+      statusText.textContent = "Error accessing microphone. Please allow microphone access.";
+    }
+    console.error(err);
+  }
+}
+
+async function stopRecording() {
+  if (wakeLock) {
+    try {
+      await wakeLock.release();
+    } catch (e) {
+      // ignore
+    }
+    wakeLock = null;
+  }
+
+  userClosing = true;
+  waitingForStop = true;
+
+  if (websocket && websocket.readyState === WebSocket.OPEN) {
+    const emptyBlob = new Blob([], { type: "audio/webm" });
+    websocket.send(emptyBlob);
+    statusText.textContent = "Recording stopped. Processing final audio...";
+  }
+
+  if (recorder) {
+    recorder.stop();
+    recorder = null;
+  }
+
+  if (microphone) {
+    microphone.disconnect();
+    microphone = null;
+  }
+
+  if (analyser) {
+    analyser = null;
+  }
+
+  if (audioContext && audioContext.state !== "closed") {
+    try {
+      await audioContext.close();
+    } catch (e) {
+      console.warn("Could not close audio context:", e);
+    }
+    audioContext = null;
+  }
+
+  if (animationFrame) {
+    cancelAnimationFrame(animationFrame);
+    animationFrame = null;
+  }
+
+  if (timerInterval) {
+    clearInterval(timerInterval);
+    timerInterval = null;
+  }
+  timerElement.textContent = "00:00";
+  startTime = null;
+
+  isRecording = false;
+  updateUI();
+}
+
+async function toggleRecording() {
+  if (!isRecording) {
+    if (waitingForStop) {
+      console.log("Waiting for stop, early return");
+      return;
+    }
+    console.log("Connecting to WebSocket");
+    try {
+      if (websocket && websocket.readyState === WebSocket.OPEN) {
+        await startRecording();
+      } else {
+        await setupWebSocket();
+        await startRecording();
+      }
+    } catch (err) {
+      statusText.textContent = "Could not connect to WebSocket or access mic. Aborted.";
+      console.error(err);
+    }
+  } else {
+    console.log("Stopping recording");
+    stopRecording();
+  }
+}
+
+function updateUI() {
+  recordButton.classList.toggle("recording", isRecording);
+  recordButton.disabled = waitingForStop;
+
+  if (waitingForStop) {
+    if (statusText.textContent !== "Recording stopped. Processing final audio...") {
+      statusText.textContent = "Please wait for processing to complete...";
+    }
+  } else if (isRecording) {
+    statusText.textContent = "Recording...";
+  } else {
+    if (
+      statusText.textContent !== "Finished processing audio! Ready to record again." &&
+      statusText.textContent !== "Processing finalized or connection closed."
+    ) {
+      statusText.textContent = "Click to start transcription";
+    }
+  }
+  if (!waitingForStop) {
+    recordButton.disabled = false;
+  }
+}
+
+recordButton.addEventListener("click", toggleRecording);

whisperlivekit/web/src/dark_mode.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M480-120q-151 0-255.5-104.5T120-480q0-138 90-239.5T440-838q13-2 23 3.5t16 14.5q6 9 6.5 21t-7.5 23q-17 26-25.5 55t-8.5 61q0 90 63 153t153 63q31 0 61.5-9t54.5-25q11-7 22.5-6.5T819-479q10 5 15.5 15t3.5 24q-14 138-117.5 229T480-120Zm0-80q88 0 158-48.5T740-375q-20 5-40 8t-40 3q-123 0-209.5-86.5T364-660q0-20 3-40t8-40q-78 32-126.5 102T200-480q0 116 82 198t198 82Zm-10-270Z"/></svg>

whisperlivekit/web/src/light_mode.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M480-360q50 0 85-35t35-85q0-50-35-85t-85-35q-50 0-85 35t-35 85q0 50 35 85t85 35Zm0 80q-83 0-141.5-58.5T280-480q0-83 58.5-141.5T480-680q83 0 141.5 58.5T680-480q0 83-58.5 141.5T480-280ZM80-440q-17 0-28.5-11.5T40-480q0-17 11.5-28.5T80-520h80q17 0 28.5 11.5T200-480q0 17-11.5 28.5T160-440H80Zm720 0q-17 0-28.5-11.5T760-480q0-17 11.5-28.5T800-520h80q17 0 28.5 11.5T920-480q0 17-11.5 28.5T880-440h-80ZM480-760q-17 0-28.5-11.5T440-800v-80q0-17 11.5-28.5T480-920q17 0 28.5 11.5T520-880v80q0 17-11.5 28.5T480-760Zm0 720q-17 0-28.5-11.5T440-80v-80q0-17 11.5-28.5T480-200q17 0 28.5 11.5T520-160v80q0 17-11.5 28.5T480-40ZM226-678l-43-42q-12-11-11.5-28t11.5-29q12-12 29-12t28 12l42 43q11 12 11 28t-11 28q-11 12-27.5 11.5T226-678Zm494 495-42-43q-11-12-11-28.5t11-27.5q11-12 27.5-11.5T734-282l43 42q12 11 11.5 28T777-183q-12 12-29 12t-28-12Zm-42-495q-12-11-11.5-27.5T678-734l42-43q11-12 28-11.5t29 11.5q12 12 12 29t-12 28l-43 42q-12 11-28 11t-28-11ZM183-183q-12-12-12-29t12-28l43-42q12-11 28.5-11t27.5 11q12 11 11.5 27.5T282-226l-42 43q-11 12-28 11.5T183-183Zm297-297Z"/></svg>

whisperlivekit/web/src/system_mode.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M396-396q-32-32-58.5-67T289-537q-5 14-6.5 28.5T281-480q0 83 58 141t141 58q14 0 28.5-2t28.5-6q-39-22-74-48.5T396-396Zm85 196q-56 0-107-21t-91-61q-40-40-61-91t-21-107q0-51 17-97.5t50-84.5q13-14 32-9.5t27 24.5q21 55 52.5 104t73.5 91q42 42 91 73.5T648-326q20 8 24.5 27t-9.5 32q-38 33-84.5 50T481-200Zm223-192q-16-5-23-20.5t-4-32.5q9-48-6-94.5T621-621q-35-35-80.5-49.5T448-677q-17 3-32-4t-21-23q-6-16 1.5-31t23.5-19q69-15 138 4.5T679-678q51 51 71 120t5 138q-4 17-19 25t-32 3ZM480-840q-17 0-28.5-11.5T440-880v-40q0-17 11.5-28.5T480-960q17 0 28.5 11.5T520-920v40q0 17-11.5 28.5T480-840Zm0 840q-17 0-28.5-11.5T440-40v-40q0-17 11.5-28.5T480-120q17 0 28.5 11.5T520-80v40q0 17-11.5 28.5T480 0Zm255-734q-12-12-12-28.5t12-28.5l28-28q11-11 27.5-11t28.5 11q12 12 12 28.5T819-762l-28 28q-12 12-28 12t-28-12ZM141-141q-12-12-12-28.5t12-28.5l28-28q12-12 28-12t28 12q12 12 12 28.5T225-169l-28 28q-11 11-27.5 11T141-141Zm739-299q-17 0-28.5-11.5T840-480q0-17 11.5-28.5T880-520h40q17 0 28.5 11.5T960-480q0 17-11.5 28.5T920-440h-40Zm-840 0q-17 0-28.5-11.5T0-480q0-17 11.5-28.5T40-520h40q17 0 28.5 11.5T120-480q0 17-11.5 28.5T80-440H40Zm779 299q-12 12-28.5 12T762-141l-28-28q-12-12-12-28t12-28q12-12 28.5-12t28.5 12l28 28q11 11 11 27.5T819-141ZM226-735q-12 12-28.5 12T169-735l-28-28q-11-11-11-27.5t11-28.5q12-12 28.5-12t28.5 12l28 28q12 12 12 28t-12 28Zm170 339Z"/></svg>

whisperlivekit/web/web_interface.py

@@ -10,4 +10,24 @@ def get_web_interface_html():
             return f.read()
     except Exception as e:
         logger.error(f"Error loading web interface HTML: {e}")
-        return "<html><body><h1>Error loading interface</h1></body></html>"
+        return "<html><body><h1>Error loading interface</h1></body></html>"
+
+
+if __name__ == '__main__':
+    
+    from fastapi import FastAPI
+    from fastapi.responses import HTMLResponse
+    import uvicorn
+    from starlette.staticfiles import StaticFiles
+    import pathlib
+    import whisperlivekit.web as webpkg
+    
+    app = FastAPI()    
+    web_dir = pathlib.Path(webpkg.__file__).parent
+    app.mount("/web", StaticFiles(directory=str(web_dir)), name="web")
+    
+    @app.get("/")
+    async def get():
+        return HTMLResponse(get_web_interface_html())
+
+    uvicorn.run(app=app)

whisperlivekit/whisper_streaming_custom/backends.py

@@ -3,32 +3,10 @@ import logging
 import io
 import soundfile as sf
 import math
-try: 
-    import torch
-except ImportError: 
-    torch = None
 from typing import List
 import numpy as np
 from whisperlivekit.timed_objects import ASRToken
-from whisperlivekit.simul_whisper.license_simulstreaming import SIMULSTREAMING_LICENSE
 logger = logging.getLogger(__name__)
-SIMULSTREAMING_ERROR_AND_INSTALLATION_INSTRUCTIONS = ImportError(
-"""SimulStreaming dependencies are not available.
-Please install WhisperLiveKit using pip install "whisperlivekit[simulstreaming]"
-""")
-
-try:
-    from whisperlivekit.simul_whisper.config import AlignAttConfig
-    from whisperlivekit.simul_whisper.simul_whisper import PaddedAlignAttWhisper, DEC_PAD
-    from whisperlivekit.simul_whisper.whisper import tokenizer
-    SIMULSTREAMING_AVAILABLE = True
-except ImportError:
-    SIMULSTREAMING_AVAILABLE = False
-    AlignAttConfig = None
-    PaddedAlignAttWhisper = None
-    DEC_PAD = None
-    tokenizer = None
-
 class ASRBase:
     sep = " "  # join transcribe words with this character (" " for whisper_timestamped,
               # "" for faster-whisper because it emits the spaces when needed)
@@ -309,181 +287,4 @@ class OpenaiApiASR(ASRBase):
         self.use_vad_opt = True
 
     def set_translate_task(self):
-        self.task = "translate"
-
-
-class SimulStreamingASR(ASRBase):
-    """SimulStreaming backend with AlignAtt policy."""
-    sep = ""
-
-    def __init__(self, lan, modelsize=None, cache_dir=None, model_dir=None, logfile=sys.stderr, **kwargs):
-        if not SIMULSTREAMING_AVAILABLE:
-            raise SIMULSTREAMING_ERROR_AND_INSTALLATION_INSTRUCTIONS
-        logger.warning(SIMULSTREAMING_LICENSE)
-        self.logfile = logfile
-        self.transcribe_kargs = {}
-        self.original_language = None if lan == "auto" else lan
-        
-        self.model_path = kwargs.get('model_path', './large-v3.pt')
-        self.frame_threshold = kwargs.get('frame_threshold', 25)
-        self.audio_max_len = kwargs.get('audio_max_len', 30.0)
-        self.audio_min_len = kwargs.get('audio_min_len', 0.0)
-        self.segment_length = kwargs.get('segment_length', 0.5)
-        self.beams = kwargs.get('beams', 1)
-        self.decoder_type = kwargs.get('decoder_type', 'greedy' if self.beams == 1 else 'beam')
-        self.task = kwargs.get('task', 'transcribe')
-        self.cif_ckpt_path = kwargs.get('cif_ckpt_path', None)
-        self.never_fire = kwargs.get('never_fire', False)
-        self.init_prompt = kwargs.get('init_prompt', None)
-        self.static_init_prompt = kwargs.get('static_init_prompt', None)
-        self.max_context_tokens = kwargs.get('max_context_tokens', None)
-        
-        if model_dir is not None:
-            self.model_path = model_dir
-        elif modelsize is not None: #For the moment the .en.pt models do not work!
-            model_mapping = {
-                'tiny': './tiny.pt',
-                'base': './base.pt',
-                'small': './small.pt',
-                'medium': './medium.pt',
-                'medium.en': './medium.en.pt',
-                'large-v1': './large-v1.pt',
-                'base.en': './base.en.pt',
-                'small.en': './small.en.pt',
-                'tiny.en': './tiny.en.pt',
-                'large-v2': './large-v2.pt',
-                'large-v3': './large-v3.pt',
-                'large': './large-v3.pt'
-            }
-            self.model_path = model_mapping.get(modelsize, f'./{modelsize}.pt')
-        
-        self.model = self.load_model(modelsize, cache_dir, model_dir)
-        
-        # Set up tokenizer for translation if needed
-        if self.task == "translate":
-            self.set_translate_task()
-
-    def load_model(self, modelsize, cache_dir, model_dir):
-        try:
-            cfg = AlignAttConfig(
-                model_path=self.model_path,
-                segment_length=self.segment_length,
-                frame_threshold=self.frame_threshold,
-                language=self.original_language,
-                audio_max_len=self.audio_max_len,
-                audio_min_len=self.audio_min_len,
-                cif_ckpt_path=self.cif_ckpt_path,
-                decoder_type="beam",
-                beam_size=self.beams,
-                task=self.task,
-                never_fire=self.never_fire,
-                init_prompt=self.init_prompt,
-                max_context_tokens=self.max_context_tokens,
-                static_init_prompt=self.static_init_prompt,
-            )
-            
-            logger.info(f"Loading SimulStreaming model with language: {self.original_language}")
-            model = PaddedAlignAttWhisper(cfg)
-            return model
-            
-        except Exception as e:
-            logger.error(f"Failed to load SimulStreaming model: {e}")
-            raise
-
-    def transcribe(self, audio, init_prompt=""):
-        """Transcribe audio using SimulStreaming."""
-        try:
-            if isinstance(audio, np.ndarray):
-                audio_tensor = torch.from_numpy(audio).float()
-            else:
-                audio_tensor = audio
-                
-            prompt = init_prompt if init_prompt else (self.init_prompt or "")
-            
-            result = self.model.infer(audio_tensor, init_prompt=prompt)
-            
-            if torch.is_tensor(result):
-                result = result[result < DEC_PAD]
-                
-            logger.debug(f"SimulStreaming transcription result: {result}")
-            return result
-            
-        except Exception as e:
-            logger.error(f"SimulStreaming transcription failed: {e}")
-            raise
-
-    def ts_words(self, result) -> List[ASRToken]:
-        """Convert SimulStreaming result to ASRToken list."""
-        tokens = []
-        
-        try:
-            if torch.is_tensor(result):
-                text = self.model.tokenizer.decode(result.cpu().numpy())
-            else:
-                text = str(result)
-                
-            if not text or len(text.strip()) == 0:
-                return tokens
-                
-            # We dont have word-level timestamps here. 1rst approach, should be improved later.
-            words = text.strip().split()
-            if not words:
-                return tokens
-            
-            duration_per_word = 0.1  # this will be modified based on actual audio duration 
-            #with the SimulStreamingOnlineProcessor
-            
-            for i, word in enumerate(words):
-                start_time = i * duration_per_word
-                end_time = (i + 1) * duration_per_word
-                
-                token = ASRToken(
-                    start=start_time,
-                    end=end_time,
-                    text=word,
-                    probability=1.0
-                )
-                tokens.append(token)
-                
-        except Exception as e:
-            logger.error(f"Error converting SimulStreaming result to tokens: {e}")
-            
-        return tokens
-
-    def segments_end_ts(self, result) -> List[float]:
-        """Get segment end timestamps."""
-        if torch.is_tensor(result):
-            num_tokens = len(result)
-            return [num_tokens * 0.1]  # rough estimate
-        return [1.0]
-
-    def use_vad(self):
-        """Enable VAD - SimulStreaming has different VAD handling."""
-        logger.info("VAD requested for SimulStreaming - handled internally by the model")
-        pass
-
-    def set_translate_task(self):
-        """Set up translation task."""
-        try:
-            self.model.tokenizer = tokenizer.get_tokenizer(
-                multilingual=True,
-                language=self.model.cfg.language,
-                num_languages=self.model.model.num_languages,
-                task="translate"
-            )
-            logger.info("SimulStreaming configured for translation task")
-        except Exception as e:
-            logger.error(f"Failed to configure SimulStreaming for translation: {e}")
-            raise
-
-    def warmup(self, audio, init_prompt=""):
-        """Warmup the SimulStreaming model."""
-        try:
-            if isinstance(audio, np.ndarray):
-                audio = torch.from_numpy(audio).float()
-            self.model.insert_audio(audio)
-            self.model.infer(True)
-            self.model.refresh_segment(complete=True)
-            logger.info("SimulStreaming model warmed up successfully")
-        except Exception as e:
-            logger.exception(f"SimulStreaming warmup failed: {e}")
+        self.task = "translate"

whisperlivekit/whisper_streaming_custom/online_asr.py

@@ -6,18 +6,6 @@ from whisperlivekit.timed_objects import ASRToken, Sentence, Transcript
 
 logger = logging.getLogger(__name__)
 
-# simulStreaming imports - we check if the files are here
-try:
-    import torch
-    from whisperlivekit.simul_whisper.config import AlignAttConfig
-    SIMULSTREAMING_AVAILABLE = True
-except ImportError:
-    logger.warning("SimulStreaming dependencies not available for online processor.")
-    SIMULSTREAMING_AVAILABLE = False
-    OnlineProcessorInterface = None
-    torch = None
-
-
 class HypothesisBuffer:
     """
     Buffer to store and process ASR hypothesis tokens.
@@ -134,6 +122,7 @@ class OnlineASRProcessor:
         self.tokenize = tokenize_method
         self.logfile = logfile
         self.confidence_validation = confidence_validation
+        self.global_time_offset = 0.0
         self.init()
 
         self.buffer_trimming_way, self.buffer_trimming_sec = buffer_trimming
@@ -164,6 +153,21 @@ class OnlineASRProcessor:
         """Append an audio chunk (a numpy array) to the current audio buffer."""
         self.audio_buffer = np.append(self.audio_buffer, audio)
 
+    def insert_silence(self, silence_duration, offset):
+        """
+        If silences are > 5s, we do a complete context clear. Otherwise, we just insert a small silence and shift the last_attend_frame
+        """
+        # if self.transcript_buffer.buffer:
+        #     self.committed.extend(self.transcript_buffer.buffer)
+        #     self.transcript_buffer.buffer = []
+            
+        if True: #silence_duration < 3: #we want the last audio to be treated to not have a gap. could also be handled in the future in ends_with_silence.
+            gap_silence = np.zeros(int(16000 * silence_duration), dtype=np.int16)
+            self.insert_audio_chunk(gap_silence)
+        else:
+            self.init(offset=silence_duration + offset)
+        self.global_time_offset += silence_duration
+
     def prompt(self) -> Tuple[str, str]:
         """
         Returns a tuple: (prompt, context), where:
@@ -242,6 +246,9 @@ class OnlineASRProcessor:
         logger.debug(
             f"Length of audio buffer now: {len(self.audio_buffer)/self.SAMPLING_RATE:.2f} seconds"
         )
+        if self.global_time_offset:
+            for token in committed_tokens:
+                token = token.with_offset(self.global_time_offset)
         return committed_tokens, current_audio_processed_upto
 
     def chunk_completed_sentence(self):
@@ -403,329 +410,3 @@ class OnlineASRProcessor:
             start = None
             end = None
         return Transcript(start, end, text, probability=probability)
-
-
-class VACOnlineASRProcessor:
-    """
-    Wraps an OnlineASRProcessor with a Voice Activity Controller (VAC).
-    
-    It receives small chunks of audio, applies VAD (e.g. with Silero),
-    and when the system detects a pause in speech (or end of an utterance)
-    it finalizes the utterance immediately.
-    """
-    SAMPLING_RATE = 16000
-
-    def __init__(self, online_chunk_size: float, *args, **kwargs):
-        self.online_chunk_size = online_chunk_size
-        self.online = OnlineASRProcessor(*args, **kwargs)
-        self.asr = self.online.asr
-        
-        # Load a VAD model (e.g. Silero VAD)
-        import torch
-        model, _ = torch.hub.load(repo_or_dir="snakers4/silero-vad", model="silero_vad")
-        from .silero_vad_iterator import FixedVADIterator
-
-        self.vac = FixedVADIterator(model)
-        self.logfile = self.online.logfile
-        self.last_input_audio_stream_end_time: float = 0.0
-        self.init()
-
-    def init(self):
-        self.online.init()
-        self.vac.reset_states()
-        self.current_online_chunk_buffer_size = 0
-        self.last_input_audio_stream_end_time = self.online.buffer_time_offset
-        self.is_currently_final = False
-        self.status: Optional[str] = None  # "voice" or "nonvoice"
-        self.audio_buffer = np.array([], dtype=np.float32)
-        self.buffer_offset = 0  # in frames
-
-    def get_audio_buffer_end_time(self) -> float:
-        """Returns the absolute end time of the audio processed by the underlying OnlineASRProcessor."""
-        return self.online.get_audio_buffer_end_time()
-
-    def clear_buffer(self):
-        self.buffer_offset += len(self.audio_buffer)
-        self.audio_buffer = np.array([], dtype=np.float32)
-
-    def insert_audio_chunk(self, audio: np.ndarray, audio_stream_end_time: float):
-        """
-        Process an incoming small audio chunk:
-          - run VAD on the chunk,
-          - decide whether to send the audio to the online ASR processor immediately,
-          - and/or to mark the current utterance as finished.
-        """
-        self.last_input_audio_stream_end_time = audio_stream_end_time
-        res = self.vac(audio)
-        self.audio_buffer = np.append(self.audio_buffer, audio)
-
-        if res is not None:
-            # VAD returned a result; adjust the frame number
-            frame = list(res.values())[0] - self.buffer_offset
-            if "start" in res and "end" not in res:
-                self.status = "voice"
-                send_audio = self.audio_buffer[frame:]
-                self.online.init(offset=(frame + self.buffer_offset) / self.SAMPLING_RATE)
-                self.online.insert_audio_chunk(send_audio)
-                self.current_online_chunk_buffer_size += len(send_audio)
-                self.clear_buffer()
-            elif "end" in res and "start" not in res:
-                self.status = "nonvoice"
-                send_audio = self.audio_buffer[:frame]
-                self.online.insert_audio_chunk(send_audio)
-                self.current_online_chunk_buffer_size += len(send_audio)
-                self.is_currently_final = True
-                self.clear_buffer()
-            else:
-                beg = res["start"] - self.buffer_offset
-                end = res["end"] - self.buffer_offset
-                self.status = "nonvoice"
-                send_audio = self.audio_buffer[beg:end]
-                self.online.init(offset=(beg + self.buffer_offset) / self.SAMPLING_RATE)
-                self.online.insert_audio_chunk(send_audio)
-                self.current_online_chunk_buffer_size += len(send_audio)
-                self.is_currently_final = True
-                self.clear_buffer()
-        else:
-            if self.status == "voice":
-                self.online.insert_audio_chunk(self.audio_buffer)
-                self.current_online_chunk_buffer_size += len(self.audio_buffer)
-                self.clear_buffer()
-            else:
-                # Keep 1 second worth of audio in case VAD later detects voice,
-                # but trim to avoid unbounded memory usage.
-                self.buffer_offset += max(0, len(self.audio_buffer) - self.SAMPLING_RATE)
-                self.audio_buffer = self.audio_buffer[-self.SAMPLING_RATE:]
-
-    def process_iter(self) -> Tuple[List[ASRToken], float]:
-        """
-        Depending on the VAD status and the amount of accumulated audio,
-        process the current audio chunk.
-        Returns a tuple: (list of committed ASRToken objects, float representing the audio processed up to time).
-        """
-        if self.is_currently_final:
-            return self.finish()
-        elif self.current_online_chunk_buffer_size > self.SAMPLING_RATE * self.online_chunk_size:
-            self.current_online_chunk_buffer_size = 0
-            return self.online.process_iter()
-        else:
-            logger.debug("No online update, only VAD")
-            return [], self.last_input_audio_stream_end_time
-
-    def finish(self) -> Tuple[List[ASRToken], float]:
-        """
-        Finish processing by flushing any remaining text.
-        Returns a tuple: (list of remaining ASRToken objects, float representing the final audio processed up to time).
-        """
-        result_tokens, processed_upto = self.online.finish()
-        self.current_online_chunk_buffer_size = 0
-        self.is_currently_final = False
-        return result_tokens, processed_upto
-    
-    def get_buffer(self):
-        """
-        Get the unvalidated buffer in string format.
-        """
-        return self.online.concatenate_tokens(self.online.transcript_buffer.buffer)
-
-
-class SimulStreamingOnlineProcessor:
-    SAMPLING_RATE = 16000
-
-    def __init__(
-        self,
-        asr,
-        tokenize_method: Optional[callable] = None,
-        buffer_trimming: Tuple[str, float] = ("segment", 15),
-        confidence_validation = False,
-        logfile=sys.stderr,
-    ):
-        if not SIMULSTREAMING_AVAILABLE:
-            raise ImportError("SimulStreaming dependencies are not available.")
-        
-        self.asr = asr
-        self.tokenize = tokenize_method
-        self.logfile = logfile
-        self.confidence_validation = confidence_validation
-        self.init()
-        
-        # buffer does not work yet
-        self.buffer_trimming_way, self.buffer_trimming_sec = buffer_trimming
-
-    def init(self, offset: Optional[float] = None):
-        """Initialize or reset the processing state."""
-        self.audio_chunks = []
-        self.offset = offset if offset is not None else 0.0
-        self.is_last = False
-        self.beg = self.offset
-        self.end = self.offset
-        self.cumulative_audio_duration = 0.0
-        self.last_audio_stream_end_time = self.offset
-        
-        self.committed: List[ASRToken] = []
-        self.last_result_tokens: List[ASRToken] = []        
-        self.buffer_content = ""
-        self.processed_audio_duration = 0.0
-
-    def get_audio_buffer_end_time(self) -> float:
-        """Returns the absolute end time of the current audio buffer."""
-        return self.end
-
-    def insert_audio_chunk(self, audio: np.ndarray, audio_stream_end_time: Optional[float] = None):
-        """Append an audio chunk to be processed by SimulStreaming."""
-        if torch is None:
-            raise ImportError("PyTorch is required for SimulStreaming but not available")
-            
-        # Convert numpy array to torch tensor
-        audio_tensor = torch.from_numpy(audio).float()
-        self.audio_chunks.append(audio_tensor)
-        
-        # Update timing
-        chunk_duration = len(audio) / self.SAMPLING_RATE
-        self.cumulative_audio_duration += chunk_duration
-        
-        if audio_stream_end_time is not None:
-            self.last_audio_stream_end_time = audio_stream_end_time
-            self.end = audio_stream_end_time
-        else:
-            self.end = self.offset + self.cumulative_audio_duration
-
-    def prompt(self) -> Tuple[str, str]:
-        """
-        Returns a tuple: (prompt, context).
-        SimulStreaming handles prompting internally, so we return empty strings.
-        """
-        return "", ""
-
-    def get_buffer(self):
-        """
-        Get the unvalidated buffer content.
-        """
-        buffer_end = self.end if hasattr(self, 'end') else None
-        return Transcript(
-            start=None, 
-            end=buffer_end, 
-            text=self.buffer_content, 
-            probability=None
-        )
-
-    def timestamped_text(self, tokens, generation):
-        # From the simulstreaming repo. self.model to self.asr.model
-        pr = generation["progress"]
-        if "result" not in generation:
-            split_words, split_tokens = self.asr.model.tokenizer.split_to_word_tokens(tokens)
-        else:
-            split_words, split_tokens = generation["result"]["split_words"], generation["result"]["split_tokens"]
-
-        frames = [p["most_attended_frames"][0] for p in pr]
-        tokens = tokens.copy()
-        ret = []
-        for sw,st in zip(split_words,split_tokens):
-            b = None
-            for stt in st:
-                t,f = tokens.pop(0), frames.pop(0)
-                if t != stt:
-                    raise ValueError(f"Token mismatch: {t} != {stt} at frame {f}.")
-                if b is None:
-                    b = f
-            e = f
-            out = (b*0.02, e*0.02, sw)
-            ret.append(out)
-            logger.debug(f"TS-WORD:\t{' '.join(map(str, out))}")
-        return ret
-
-    def process_iter(self) -> Tuple[List[ASRToken], float]:
-        """
-        Process accumulated audio chunks using SimulStreaming.
-        
-        Returns a tuple: (list of committed ASRToken objects, float representing the audio processed up to time).
-        """
-        if not self.audio_chunks:
-            return [], self.end
-
-        try:
-            # concatenate all audio chunks
-            if len(self.audio_chunks) == 1:
-                audio = self.audio_chunks[0]
-            else:
-                audio = torch.cat(self.audio_chunks, dim=0)
-            
-            audio_duration = audio.shape[0] / self.SAMPLING_RATE if audio.shape[0] > 0 else 0
-            self.processed_audio_duration += audio_duration
-            
-            self.audio_chunks = []
-            
-            logger.debug(f"SimulStreaming processing audio shape: {audio.shape}, duration: {audio_duration:.2f}s")
-            logger.debug(f"Current end time: {self.end:.2f}s, last stream time: {self.last_audio_stream_end_time:.2f}s")
-            
-            self.asr.model.insert_audio(audio)
-            tokens, generation_progress = self.asr.model.infer(is_last=self.is_last)
-            ts_words = self.timestamped_text(tokens, generation_progress)
-            text = self.asr.model.tokenizer.decode(tokens)
-            
-            new_tokens = []
-            for ts_word in ts_words:
-                
-                start, end, word = ts_word
-                token = ASRToken(
-                    start=start,
-                    end=end,
-                    text=word,
-                    probability=0.95  # fake prob. Maybe we can extract it from the model?
-                )
-                new_tokens.append(token)
-                self.committed.extend(new_tokens)
-            
-            return new_tokens, self.end
-
-            
-        except Exception as e:
-            logger.exception(f"SimulStreaming processing error: {e}")
-            return [], self.end
-
-    def finish(self) -> Tuple[List[ASRToken], float]:
-        logger.debug("SimulStreaming finish() called")
-        self.is_last = True        
-        final_tokens, final_time = self.process_iter()
-        self.is_last = False
-        return final_tokens, final_time
-
-    def concatenate_tokens(
-        self,
-        tokens: List[ASRToken],
-        sep: Optional[str] = None,
-        offset: float = 0
-    ) -> Transcript:
-        """Concatenate tokens into a Transcript object."""
-        sep = sep if sep is not None else self.asr.sep
-        text = sep.join(token.text for token in tokens)
-        probability = sum(token.probability for token in tokens if token.probability) / len(tokens) if tokens else None
-        if tokens:
-            start = offset + tokens[0].start
-            end = offset + tokens[-1].end
-        else:
-            start = None
-            end = None
-        return Transcript(start, end, text, probability=probability)
-
-    def chunk_at(self, time: float):
-        """
-        useless but kept for compatibility
-        """
-        logger.debug(f"SimulStreaming chunk_at({time:.2f}) - handled internally")
-        pass
-
-    def words_to_sentences(self, tokens: List[ASRToken]) -> List[Sentence]:
-        """
-        Create simple sentences.
-        """
-        if not tokens:
-            return []
-        
-        full_text = " ".join(token.text for token in tokens)
-        sentence = Sentence(
-            start=tokens[0].start,
-            end=tokens[-1].end,
-            text=full_text
-        )
-        return [sentence]

whisperlivekit/whisper_streaming_custom/whisper_online.py

@@ -5,8 +5,7 @@ import librosa
 from functools import lru_cache
 import time
 import logging
-from .backends import FasterWhisperASR, MLXWhisper, WhisperTimestampedASR, OpenaiApiASR, SimulStreamingASR, SIMULSTREAMING_AVAILABLE, SIMULSTREAMING_ERROR_AND_INSTALLATION_INSTRUCTIONS
-from .online_asr import OnlineASRProcessor, VACOnlineASRProcessor, SimulStreamingOnlineProcessor, SIMULSTREAMING_AVAILABLE as SIMULSTREAMING_ONLINE_AVAILABLE
+from .backends import FasterWhisperASR, MLXWhisper, WhisperTimestampedASR, OpenaiApiASR
 
 logger = logging.getLogger(__name__)
 
@@ -68,35 +67,7 @@ def backend_factory(args):
     backend = args.backend
     if backend == "openai-api":
         logger.debug("Using OpenAI API.")
-        asr = OpenaiApiASR(lan=args.lan)
-    elif backend == "simulstreaming":
-        logger.debug("Using SimulStreaming backend.")
-        if not SIMULSTREAMING_AVAILABLE:
-            raise SIMULSTREAMING_ERROR_AND_INSTALLATION_INSTRUCTIONS
-        
-        simulstreaming_kwargs = {}
-        for attr in ['frame_threshold', 'beams', 'decoder_type', 'audio_max_len', 'audio_min_len', 
-                     'cif_ckpt_path', 'never_fire', 'init_prompt', 'static_init_prompt', 
-                     'max_context_tokens', 'model_path']:
-            if hasattr(args, attr):
-                simulstreaming_kwargs[attr] = getattr(args, attr)
-        
-        # Add segment_length from min_chunk_size
-        simulstreaming_kwargs['segment_length'] = getattr(args, 'min_chunk_size', 0.5)
-        simulstreaming_kwargs['task'] = args.task
-        
-        size = args.model
-        t = time.time()
-        logger.info(f"Loading SimulStreaming {size} model for language {args.lan}...")
-        asr = SimulStreamingASR(
-            modelsize=size,
-            lan=args.lan,
-            cache_dir=getattr(args, 'model_cache_dir', None),
-            model_dir=getattr(args, 'model_dir', None),
-            **simulstreaming_kwargs
-        )
-        e = time.time()
-        logger.info(f"done. It took {round(e-t,2)} seconds.")
+        asr = OpenaiApiASR(lan=args.lan)        
     else:
         if backend == "faster-whisper":
             asr_cls = FasterWhisperASR
@@ -136,107 +107,4 @@ def backend_factory(args):
         tokenizer = create_tokenizer(tgt_language)
     else:
         tokenizer = None
-    return asr, tokenizer
-
-def online_factory(args, asr, tokenizer, logfile=sys.stderr):
-    if args.backend == "simulstreaming":
-        if not SIMULSTREAMING_ONLINE_AVAILABLE:
-            raise SIMULSTREAMING_ERROR_AND_INSTALLATION_INSTRUCTIONS
-        
-        logger.debug("Creating SimulStreaming online processor")
-        online = SimulStreamingOnlineProcessor(
-            asr,
-            tokenizer,
-            logfile=logfile,
-            buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec),
-            confidence_validation=args.confidence_validation
-        )
-    elif args.vac:
-        online = VACOnlineASRProcessor(
-            args.min_chunk_size,
-            asr,
-            tokenizer,
-            logfile=logfile,
-            buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec),
-            confidence_validation = args.confidence_validation
-        )
-    else:
-        online = OnlineASRProcessor(
-            asr,
-            tokenizer,
-            logfile=logfile,
-            buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec),
-            confidence_validation = args.confidence_validation
-        )
-    return online
-  
-def asr_factory(args, logfile=sys.stderr):
-    """
-    Creates and configures an ASR and ASR Online instance based on the specified backend and arguments.
-    """
-    asr, tokenizer = backend_factory(args)
-    online = online_factory(args, asr, tokenizer, logfile=logfile)
-    return asr, online
-
-def warmup_asr(asr, warmup_file=None, timeout=5):
-    """
-    Warmup the ASR model by transcribing a short audio file.
-    """
-    import os
-    import tempfile
-    
-    is_simulstreaming = hasattr(asr, 'warmup') and callable(getattr(asr, 'warmup'))
-    
-    if warmup_file is None:
-        # Download JFK sample if not already present
-        jfk_url = "https://github.com/ggerganov/whisper.cpp/raw/master/samples/jfk.wav"
-        temp_dir = tempfile.gettempdir()
-        warmup_file = os.path.join(temp_dir, "whisper_warmup_jfk.wav")
-        
-        if not os.path.exists(warmup_file):
-            logger.debug(f"Downloading warmup file from {jfk_url}")
-            print(f"Downloading warmup file from {jfk_url}")
-            import time
-            import urllib.request
-            import urllib.error
-            import socket
-            
-            original_timeout = socket.getdefaulttimeout()
-            socket.setdefaulttimeout(timeout)
-            
-            start_time = time.time()
-            try:
-                urllib.request.urlretrieve(jfk_url, warmup_file)
-                logger.debug(f"Download successful in {time.time() - start_time:.2f}s")
-            except (urllib.error.URLError, socket.timeout) as e:
-                logger.warning(f"Download failed: {e}. Proceeding without warmup.")
-                return False
-            finally:
-                socket.setdefaulttimeout(original_timeout)
-    elif not warmup_file:
-        return False 
-    
-    if not warmup_file or not os.path.exists(warmup_file) or os.path.getsize(warmup_file) == 0:
-        logger.warning(f"Warmup file {warmup_file} invalid or missing.")
-        return False
-    
-    print(f"Warming up {'SimulStreaming' if is_simulstreaming else 'Whisper'} with {warmup_file}")
-    try:
-        import librosa
-        audio, sr = librosa.load(warmup_file, sr=16000)
-    except Exception as e:
-        logger.warning(f"Failed to load audio file: {e}")
-        return False
-    
-    try:
-        if is_simulstreaming:
-            asr.warmup(audio)
-        else:
-            asr.transcribe(audio)
-        
-        logger.info(f"{'SimulStreaming' if is_simulstreaming else 'Whisper'} is warmed up")
-        return True
-        
-    except Exception as e:
-        logger.warning(f"Warmup failed: {e}")
-        return False
+    return asr, tokenizer