to 0.2.9

support for raw PCM input option by @YeonjunNotFR
add --disable-punctuation-split option
2026-03-07 22:33:36 +00:00 · 2025-09-11 21:36:32 +02:00 · 2025-09-11 21:32:11 +02:00 · 2025-09-11 21:03:00 +02:00 · 2025-09-11 21:03:00 +02:00 · 2025-09-11 21:03:00 +02:00
51 changed files with 3013 additions and 311 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -137,4 +137,5 @@ run_*.sh
 test_*.py
 launch.json
 .DS_Store
-test/*
+test/*
+nllb-200-distilled-600M-ctranslate2/*
--- a/DEV_NOTES.md
+++ b/DEV_NOTES.md
@@ -0,0 +1,70 @@
+# 1. Simulstreaming: Decouple the encoder for faster inference
+
+Simulstreaming encoder time (whisperlivekit/simul_whisper/simul_whisper.py l. 397) experimentations :
+
+On macOS Apple Silicon M4 :
+
+| Encoder | base.en | small |
+|--------|---------|-------|
+| WHISPER (no modification) | 0.35s | 1.09s |
+| FASTER_WHISPER | 0.4s | 1.20s |
+| MLX_WHISPER | 0.07s | 0.20s |
+
+Memory saved by only loading encoder for optimized framework:
+
+For tiny.en, mlx whisper:
+Sizes MLX whisper:
+Decoder weights: 59110771 bytes
+Encoder weights: 15268874 bytes
+
+
+
+# 2. SortFormer Diarization: 4-to-2 Speaker Constraint Algorithm
+
+Transform a diarization model that predicts up to 4 speakers into one that predicts up to 2 speakers by mapping the output predictions.
+
+## Problem Statement
+- Input: `self.total_preds` with shape `(x, x, 4)` - predictions for 4 speakers
+- Output: Constrained predictions with shape `(x, x, 2)` - predictions for 2 speakers
+
+#
+### Initial Setup
+For each time step `i`, we have a ranking of 4 speaker predictions (1-4). When only 2 speakers are present, the model will have close predictions for the 2 active speaker positions.
+
+Instead of `np.argmax(preds_np, axis=1)`, we take the top 2 predictions and build a dynamic 4→2 mapping that can evolve over time.
+
+### Algorithm
+
+```python
+top_2_speakers = np.argsort(preds_np, axis=1)[:, -2:]
+```
+
+- `DS_a_{i}`: Top detected speaker for prediction i
+- `DS_b_{i}`: Second detected speaker for prediction i  
+- `AS_{i}`: Attributed speaker for prediction i
+- `GTS_A`: Ground truth speaker A
+- `GTS_B`: Ground truth speaker B
+- `DIST(a, b)`: Distance between detected speakers a and b
+
+3. **Attribution Logic**
+
+```
+AS_0 ← A
+
+AS_1 ← B
+
+IF DIST(DS_a_0, DS_a_1) < DIST(DS_a_0, DS_a_2) AND 
+    DIST(DS_a_0, DS_a_1) < DIST(DS_a_1, DS_a_2):
+    # Likely that DS_a_0 = DS_a_1 (same speaker)
+    AS_1 ← A
+    AS_2 ← B
+
+ELIF DIST(DS_a_0, DS_a_2) < DIST(DS_a_0, DS_a_1) AND 
+    DIST(DS_a_0, DS_a_2) < DIST(DS_a_1, DS_a_2):
+    AS_2 ← A
+
+ELSE:
+    AS_2 ← B
+
+to finish
+```
--- a/31
+++ b/31
@@ -17,18 +17,26 @@ RUN apt-get update && \
        ffmpeg \
        git \
        build-essential \
-        python3-dev && \
+        python3-dev \
+        ca-certificates && \
    rm -rf /var/lib/apt/lists/*

 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
+
+# timeout/retries for large torch wheels
+RUN pip3 install --upgrade pip setuptools wheel && \
+    pip3 --disable-pip-version-check install --timeout=120 --retries=5 \
+        --index-url https://download.pytorch.org/whl/cu129 \
+        torch torchaudio \
+    || (echo "Initial install failed — retrying with extended timeout..." && \
+        pip3 --disable-pip-version-check install --timeout=300 --retries=3 \
+            --index-url https://download.pytorch.org/whl/cu129 \
+            torch torchvision torchaudio)

 COPY . .

 # Install WhisperLiveKit directly, allowing for optional dependencies
-#   Note: For gates models, need to add your HF toke. See README.md
-#         for more details.
 RUN if [ -n "$EXTRAS" ]; then \
      echo "Installing with extras: [$EXTRAS]"; \
      pip install --no-cache-dir whisperlivekit[$EXTRAS]; \
@@ -37,16 +45,14 @@ RUN if [ -n "$EXTRAS" ]; then \
      pip install --no-cache-dir whisperlivekit; \
    fi

-# Enable in-container caching for Hugging Face models by: 
-# Note: If running multiple containers, better to map a shared
-# bucket. 
-#
+# In-container caching for Hugging Face models by: 
 # A) Make the cache directory persistent via an anonymous volume.
 #    Note: This only persists for a single, named container. This is 
 #          only for convenience at de/test stage. 
 #          For prod, it is better to use a named volume via host mount/k8s.
 VOLUME ["/root/.cache/huggingface/hub"]

+
 # or
 # B) Conditionally copy a local pre-cache from the build context to the 
 #    container's cache via the HF_PRECACHE_DIR build-arg.
@@ -61,8 +67,7 @@ RUN if [ -n "$HF_PRECACHE_DIR" ]; then \
      echo "No local Hugging Face cache specified, skipping copy"; \
    fi

-# Conditionally copy a Hugging Face token if provided
-
+# Conditionally copy a Hugging Face token if provided. Useful for Diart backend (pyannote audio models)
 RUN if [ -n "$HF_TKN_FILE" ]; then \
      echo "Copying Hugging Face token from $HF_TKN_FILE"; \
      mkdir -p /root/.cache/huggingface && \
@@ -70,11 +75,9 @@ RUN if [ -n "$HF_TKN_FILE" ]; then \
    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
-CMD ["--model", "medium"]
+CMD ["--model", "medium"]
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@
 <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=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://pypi.org/project/whisperlivekit/"><img alt="Python Versions" src="https://img.shields.io/badge/python-3.9--3.15-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>

@@ -19,6 +19,7 @@ Real-time speech transcription directly to your browser, with a ready-to-use bac
 #### Powered by Leading Research:

 - [SimulStreaming](https://github.com/ufal/SimulStreaming) (SOTA 2025) - Ultra-low latency transcription with AlignAtt policy
+- [NLLB](https://arxiv.org/abs/2207.04672), ([distilled](https://huggingface.co/entai2965/nllb-200-distilled-600M-ctranslate2)) (2024) - Translation to more than 100 languages.
 - [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
@@ -39,6 +40,8 @@ Real-time speech transcription directly to your browser, with a ready-to-use bac
 ```bash
 pip install whisperlivekit
 ```
+> You can also clone the repo and `pip install -e .` for the latest version.
+

 >  **FFmpeg is required** and must be installed before using WhisperLiveKit
 > 
@@ -67,10 +70,11 @@ pip install whisperlivekit
 | 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` |
+| **Apple Silicon optimized backend** | `mlx-whisper` |
+| **NLLB Translation** | `huggingface_hub` & `transformers` |
+| *[Not recommanded]*  Speaker diarization with Diart | `diart` |
+| *[Not recommanded]*  Original Whisper backend | `whisper` |
+| *[Not recommanded]*  Improved timestamps backend | `whisper-timestamped` |
 | OpenAI API backend | `openai` |

 See  **Parameters & Configuration** below on how to use them.
@@ -128,7 +132,7 @@ async def websocket_endpoint(websocket: WebSocket):
        await audio_processor.process_audio(message)        
 ```

-**Frontend Implementation**: 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()`
+**Frontend Implementation**: 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_inline_ui_html` & `page = get_inline_ui_html()`


 ## Parameters & Configuration
@@ -138,16 +142,19 @@ An important list of parameters can be changed. But what *should* you change?
 - the `--language`.  List [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py). If you use `auto`, the model attempts to detect the language automatically, but it tends to bias towards English.
 - 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
+- `--task translate`, to translate in english
 - `--host`, `--port`, `--ssl-certfile`, `--ssl-keyfile`, if you set up a server
 - `--diarization`, if you want to use it.
+- [BETA] `--target-language`, to translate using NLLB. [118 languages available](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/translation/mapping_languages.py). If you want to translate to english, you should rather use `--task translate`, since Whisper can do it directly.

-The rest I don't recommend. But below are your options.
+### Full list of parameters :

 | Parameter | Description | Default |
 |-----------|-------------|---------|
 | `--model` | Whisper model size. | `small` |
 | `--language` | Source language code or `auto` | `auto` |
-| `--task` | `transcribe` or `translate` | `transcribe` |
+| `--task` | Set to `translate` to translate to english | `transcribe` |
+| `--target-language` | [BETA] Translation language target. Ex: `fr` | `None` |
 | `--backend` | Processing backend | `simulstreaming` |
 | `--min-chunk-size` | Minimum audio chunk size (seconds) | `1.0` |
 | `--no-vac` | Disable Voice Activity Controller | `False` |
@@ -157,16 +164,12 @@ The rest I don't recommend. But below are your options.
 | `--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` |
-
-
-| WhisperStreaming backend options | Description | Default |
-|-----------|-------------|---------|
-| `--confidence-validation` | Use confidence scores for faster validation | `False` |
-| `--buffer_trimming` | Buffer trimming strategy (`sentence` or `segment`) | `segment` |
+| `--pcm-input` | raw PCM (s16le) data is expected as input and FFmpeg will be bypassed. | `False` |


 | SimulStreaming backend options | Description | Default |
 |-----------|-------------|---------|
+| `--disable-fast-encoder` | Disable Faster Whisper or MLX Whisper backends for the encoder (if installed). Inference can be slower but helpful when GPU memory is limited | `False` |
 | `--frame-threshold` | AlignAtt frame threshold (lower = faster, higher = more accurate) | `25` |
 | `--beams` | Number of beams for beam search (1 = greedy decoding) | `1` |
 | `--decoder` | Force decoder type (`beam` or `greedy`) | `auto` |
@@ -178,12 +181,19 @@ The rest I don't recommend. But below are your 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` |
+| `--preload-model-count` | Optional. Number of models to preload in memory to speed up loading (set up to the expected number of concurrent users) | `1` |
+
+
+| WhisperStreaming backend options | Description | Default |
+|-----------|-------------|---------|
+| `--confidence-validation` | Use confidence scores for faster validation | `False` |
+| `--buffer_trimming` | Buffer trimming strategy (`sentence` or `segment`) | `segment` |

 | Diarization options | Description | Default |
 |-----------|-------------|---------|
 | `--diarization` | Enable speaker identification | `False` |
 | `--diarization-backend` |  `diart` or `sortformer` | `sortformer` |
+| `--disable-punctuation-split` |  Disable punctuation based splits. See #214 | `False` |
 | `--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` |

--- a/ReadmeJP.md
+++ b/ReadmeJP.md
@@ -0,0 +1,258 @@
+<h1 align="center">WhisperLiveKit</h1>
+
+<p align="center">
+<img src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/demo.png" alt="WhisperLiveKit Demo" width="730">
+</p>
+
+<p align="center"><b>話者識別機能付き、リアルタイム、完全ローカルな音声テキスト変換</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=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>
+
+すぐに使えるバックエンド+サーバーとシンプルなフロントエンドで、リアルタイムの音声文字起こしをブラウザに直接提供します。✨
+
+#### 主要な研究による技術：
+
+- [SimulStreaming](https://github.com/ufal/SimulStreaming) (SOTA 2025) - AlignAttポリシーによる超低遅延文字起こし
+- [WhisperStreaming](https://github.com/ufal/whisper_streaming) (SOTA 2023) - LocalAgreementポリシーによる低遅延文字起こし
+- [Streaming Sortformer](https://arxiv.org/abs/2507.18446) (SOTA 2025) - 高度なリアルタイム話者ダイアライゼーション
+- [Diart](https://github.com/juanmc2005/diart) (SOTA 2021) - リアルタイム話者ダイアライゼーション
+- [Silero VAD](https://github.com/snakers4/silero-vad) (2024) - エンタープライズグレードの音声区間検出
+
+> **なぜ各音声バッチで単純なWhisperモデルを実行しないのか？** Whisperは完全な発話向けに設計されており、リアルタイムのチャンク向けではありません。小さなセグメントを処理するとコンテキストが失われ、単語が音節の途中で途切れ、質の悪い文字起こしになります。WhisperLiveKitは、インテリジェントなバッファリングとインクリメンタルな処理のために、最先端の同時音声研究を利用しています。
+
+### アーキテクチャ
+
+<img alt="Architecture" src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/architecture.png" />
+
+*バックエンドは複数の同時ユーザーをサポートします。音声が検出されない場合、音声区間検出がオーバーヘッドを削減します。*
+
+### インストールとクイックスタート
+
+```bash
+pip install whisperlivekit
+```
+
+>  **FFmpegが必要です** WhisperLiveKitを使用する前にインストールする必要があります。
+>
+> | OS | インストール方法 |
+> |-----------|-------------|
+>  | Ubuntu/Debian | `sudo apt install ffmpeg` |
+> | MacOS | `brew install ffmpeg` |
+> | Windows | https://ffmpeg.org/download.html から.exeをダウンロードし、PATHに追加 |
+
+#### クイックスタート
+1. **文字起こしサーバーを起動します:**
+   ```bash
+   whisperlivekit-server --model base --language en
+   ```
+
+2. **ブラウザを開き** `http://localhost:8000` にアクセスします。話し始めると、あなたの言葉がリアルタイムで表示されます！
+
+
+> - 利用可能なすべての言語のリストについては、[tokenizer.py](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py) を参照してください。
+> - HTTPSの要件については、**パラメータ**セクションのSSL設定オプションを参照してください。
+
+#### オプションの依存関係
+
+| オプション | `pip install` |
+|-----------|-------------|
+| **Sortformerによる話者ダイアライゼーション** | `git+https://github.com/NVIDIA/NeMo.git@main#egg=nemo_toolkit[asr]` |
+| Diartによる話者ダイアライゼーション | `diart` |
+| オリジナルのWhisperバックエンド | `whisper` |
+| タイムスタンプ改善バックエンド | `whisper-timestamped` |
+| Apple Silicon最適化バックエンド | `mlx-whisper` |
+| OpenAI APIバックエンド | `openai` |
+
+それらの使用方法については、以下の**パラメータと設定**を参照してください。
+
+### 使用例
+
+**コマンドラインインターフェース**: 様々なオプションで文字起こしサーバーを起動します:
+
+```bash
+# デフォルト(small)より良いモデルを使用
+whisperlivekit-server --model large-v3
+
+# ダイアライゼーションと言語を指定した高度な設定
+whisperlivekit-server --host 0.0.0.0 --port 8000 --model medium --diarization --language fr
+```
+
+**Python API連携**: 関数やクラスの使用方法のより完全な例については、[basic_server](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/basic_server.py) を確認してください。
+
+```python
+from whisperlivekit import TranscriptionEngine, AudioProcessor, parse_args
+from fastapi import FastAPI, WebSocket, WebSocketDisconnect
+from fastapi.responses import HTMLResponse
+from contextlib import asynccontextmanager
+import asyncio
+
+transcription_engine = None
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    global transcription_engine
+    transcription_engine = TranscriptionEngine(model="medium", diarization=True, lan="en")
+    yield
+
+app = FastAPI(lifespan=lifespan)
+
+async def handle_websocket_results(websocket: WebSocket, results_generator):
+    async for response in results_generator:
+        await websocket.send_json(response)
+    await websocket.send_json({"type": "ready_to_stop"})
+
+@app.websocket("/asr")
+async def websocket_endpoint(websocket: WebSocket):
+    global transcription_engine
+
+    # 接続ごとに新しいAudioProcessorを作成し、共有エンジンを渡す
+    audio_processor = AudioProcessor(transcription_engine=transcription_engine)
+    results_generator = await audio_processor.create_tasks()
+    results_task = asyncio.create_task(handle_websocket_results(websocket, results_generator))
+    await websocket.accept()
+    while True:
+        message = await websocket.receive_bytes()
+        await audio_processor.process_audio(message)
+```
+
+**フロントエンド実装**: パッケージにはHTML/JavaScript実装が[ここ](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/web/live_transcription.html)に含まれています。`from whisperlivekit import get_web_interface_html` & `page = get_web_interface_html()` を使ってインポートすることもできます。
+
+
+## パラメータと設定
+
+重要なパラメータのリストを変更できます。しかし、何を*変更すべき*でしょうか？
+- `--model` サイズ。リストと推奨事項は[こちら](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/available_models.md)
+- `--language`。リストは[こちら](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py)。`auto`を使用すると、モデルは自動的に言語を検出しようとしますが、英語に偏る傾向があります。
+- `--backend`？ `simulstreaming`が正しく動作しない場合や、デュアルライセンス要件を避けたい場合は`--backend faster-whisper`に切り替えることができます。
+- `--warmup-file`、もしあれば
+- `--host`, `--port`, `--ssl-certfile`, `--ssl-keyfile`、サーバーをセットアップする場合
+- `--diarization`、使用したい場合。
+
+残りは推奨しません。しかし、以下があなたのオプションです。
+
+| パラメータ | 説明 | デフォルト |
+|-----------|-------------|---------|
+| `--model` | Whisperモデルのサイズ。 | `small` |
+| `--language` | ソース言語コードまたは`auto` | `auto` |
+| `--task` | `transcribe`または`translate` | `transcribe` |
+| `--backend` | 処理バックエンド | `simulstreaming` |
+| `--min-chunk-size` | 最小音声チャンクサイズ（秒） | `1.0` |
+| `--no-vac` | 音声アクティビティコントローラーを無効化 | `False` |
+| `--no-vad` | 音声区間検出を無効化 | `False` |
+| `--warmup-file` | モデルのウォームアップ用音声ファイルパス | `jfk.wav` |
+| `--host` | サーバーホストアドレス | `localhost` |
+| `--port` | サーバーポート | `8000` |
+| `--ssl-certfile` | SSL証明書ファイルへのパス（HTTPSサポート用） | `None` |
+| `--ssl-keyfile` | SSL秘密鍵ファイルへのパス（HTTPSサポート用） | `None` |
+
+
+| WhisperStreamingバックエンドオプション | 説明 | デフォルト |
+|-----------|-------------|---------|
+| `--confidence-validation` | 高速な検証のために信頼スコアを使用 | `False` |
+| `--buffer_trimming` | バッファトリミング戦略（`sentence`または`segment`） | `segment` |
+
+
+| SimulStreamingバックエンドオプション | 説明 | デフォルト |
+|-----------|-------------|---------|
+| `--frame-threshold` | AlignAttフレームしきい値（低いほど速く、高いほど正確） | `25` |
+| `--beams` | ビームサーチのビーム数（1 = 貪欲デコーディング） | `1` |
+| `--decoder` | デコーダタイプを強制（`beam`または`greedy`） | `auto` |
+| `--audio-max-len` | 最大音声バッファ長（秒） | `30.0` |
+| `--audio-min-len` | 処理する最小音声長（秒） | `0.0` |
+| `--cif-ckpt-path` | 単語境界検出用CIFモデルへのパス | `None` |
+| `--never-fire` | 未完了の単語を決して切り捨てない | `False` |
+| `--init-prompt` | モデルの初期プロンプト | `None` |
+| `--static-init-prompt` | スクロールしない静的プロンプト | `None` |
+| `--max-context-tokens` | 最大コンテキストトークン数 | `None` |
+| `--model-path` | .ptモデルファイルへの直接パス。見つからない場合はダウンロード | `./base.pt` |
+| `--preloaded-model-count` | オプション。メモリにプリロードするモデルの数（予想される同時ユーザー数まで設定） | `1` |
+
+| ダイアライゼーションオプション | 説明 | デフォルト |
+|-----------|-------------|---------|
+| `--diarization` | 話者識別を有効化 | `False` |
+| `--diarization-backend` | `diart`または`sortformer` | `sortformer` |
+| `--segmentation-model` | DiartセグメンテーションモデルのHugging FaceモデルID。[利用可能なモデル](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `pyannote/segmentation-3.0` |
+| `--embedding-model` | Diart埋め込みモデルのHugging FaceモデルID。[利用可能なモデル](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `speechbrain/spkrec-ecapa-voxceleb` |
+
+
+> Diartを使用したダイアライゼーションには、pyannote.audioモデルへのアクセスが必要です：
+> 1. `pyannote/segmentation`モデルの[ユーザー条件に同意](https://huggingface.co/pyannote/segmentation)
+> 2. `pyannote/segmentation-3.0`モデルの[ユーザー条件に同意](https://huggingface.co/pyannote/segmentation-3.0)
+> 3. `pyannote/embedding`モデルの[ユーザー条件に同意](https://huggingface.co/pyannote/embedding)
+>4. HuggingFaceでログイン: `huggingface-cli login`
+
+### 🚀 デプロイガイド
+
+WhisperLiveKitを本番環境にデプロイするには：
+
+1. **サーバーセットアップ**: 本番用ASGIサーバーをインストールし、複数のワーカーで起動します
+   ```bash
+   pip install uvicorn gunicorn
+   gunicorn -k uvicorn.workers.UvicornWorker -w 4 your_app:app
+   ```
+
+2. **フロントエンド**: カスタマイズした`html`のバージョンをホストし、WebSocket接続が正しくポイントするようにします
+
+3. **Nginx設定** (本番環境で推奨):
+    ```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;
+    }}
+    ```
+
+4. **HTTPSサポート**: 安全なデプロイメントのために、WebSocket URLで "ws://" の代わりに "wss://" を使用します
+
+## 🐋 Docker
+
+GPUまたはCPUサポート付きでDockerを使用してアプリケーションを簡単にデプロイします。
+
+### 前提条件
+- Dockerがシステムにインストールされていること
+- GPUサポートの場合: NVIDIA Dockerランタイムがインストールされていること
+
+### クイックスタート
+
+**GPUアクセラレーション付き (推奨):**
+```bash
+docker build -t wlk .
+docker run --gpus all -p 8000:8000 --name wlk wlk
+```
+
+**CPUのみ:**
+```bash
+docker build -f Dockerfile.cpu -t wlk .
+docker run -p 8000:8000 --name wlk wlk
+```
+
+### 高度な使用法
+
+**カスタム設定:**
+```bash
+# カスタムモデルと言語の例
+docker run --gpus all -p 8000:8000 --name wlk wlk --model large-v3 --language fr
+```
+
+### メモリ要件
+- **大規模モデル**: Dockerランタイムに十分なメモリが割り当てられていることを確認してください
+
+
+#### カスタマイズ
+
+- `--build-arg` オプション:
+  - `EXTRAS="whisper-timestamped"` - イメージのインストールにエクストラを追加します（スペースなし）。必要なコンテナオプションを設定することを忘れないでください！
+  - `HF_PRECACHE_DIR="./.cache/"` - 初回起動を高速化するためにモデルキャッシュをプリロードします
+  - `HF_TKN_FILE="./token"` - ゲート付きモデルをダウンロードするためにHugging Face Hubアクセストークンを追加します
+
+## 🔮 ユースケース
+会議の文字起こしのためにリアルタイムで議論をキャプチャする、聴覚障害のあるユーザーがアクセシビリティツールを通じて会話を追うのを助ける、コンテンツ作成のためにポッドキャストやビデオを自動的に文字起こしする、カスタマーサービスのために話者識別付きでサポートコールを文字起こしする...
--- a/architecture.png
+++ b/architecture.png
--- a/available_models.md
+++ b/available_models.md
@@ -58,6 +58,7 @@
 - `small`: ~2GB VRAM
 - `medium`: ~5GB VRAM
 - `large`: ~10GB VRAM
+- `large‑v3‑turbo`: ~6GB VRAM

 **Audio Quality Impact**:
 - Clean, clear audio: smaller models may suffice
--- a/chrome-extension/README.md
+++ b/chrome-extension/README.md
@@ -0,0 +1,17 @@
+## WhisperLiveKit Chrome Extension v0.1.0
+Capture the audio of your current tab, transcribe or translate it using WhisperliveKit. **Still unstable**
+
+<img src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/chrome-extension/demo-extension.png" alt="WhisperLiveKit Demo" width="730">
+
+## Running this extension
+1. Clone this repository.
+2. Load this directory in Chrome as an unpacked extension.
+
+
+## Devs:
+- Impossible to capture audio from tabs if extension is a pannel, unfortunately: 
+- https://issues.chromium.org/issues/40926394
+- https://groups.google.com/a/chromium.org/g/chromium-extensions/c/DET2SXCFnDg
+- https://issues.chromium.org/issues/40916430
+
+- To capture microphone in an extension, there are tricks: https://github.com/justinmann/sidepanel-audio-issue , https://medium.com/@lynchee.owo/how-to-enable-microphone-access-in-chrome-extensions-by-code-924295170080 (comments)
--- a/chrome-extension/background.js
+++ b/chrome-extension/background.js
@@ -0,0 +1,9 @@
+chrome.runtime.onInstalled.addListener((details) => {
+    if (details.reason.search(/install/g) === -1) {
+        return
+    }
+    chrome.tabs.create({
+        url: chrome.runtime.getURL("welcome.html"),
+        active: true
+    })
+})
--- a/chrome-extension/demo-extension.png
+++ b/chrome-extension/demo-extension.png
--- a/chrome-extension/icons/icon128.png
+++ b/chrome-extension/icons/icon128.png
--- a/chrome-extension/icons/icon16.png
+++ b/chrome-extension/icons/icon16.png
--- a/chrome-extension/icons/icon32.png
+++ b/chrome-extension/icons/icon32.png
--- a/chrome-extension/icons/icon48.png
+++ b/chrome-extension/icons/icon48.png
--- a/chrome-extension/live_transcription.js
+++ b/chrome-extension/live_transcription.js
@@ -0,0 +1,669 @@
+/* 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;
+let availableMicrophones = [];
+let selectedMicrophoneId = 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"]');
+const microphoneSelect = document.getElementById("microphoneSelect");
+const settingsToggle = document.getElementById("settingsToggle");
+const settingsDiv = document.querySelector(".settings");
+
+
+
+chrome.runtime.onInstalled.addListener((details) => {
+    if (details.reason.search(/install/g) === -1) {
+        return
+    }
+    chrome.tabs.create({
+        url: chrome.runtime.getURL("welcome.html"),
+        active: true
+    })
+})
+
+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);
+}
+
+async function enumerateMicrophones() {
+  try {
+      const micPermission = await navigator.permissions.query({
+    name: "microphone",
+  });
+  
+    const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+    stream.getTracks().forEach(track => track.stop());
+
+    const devices = await navigator.mediaDevices.enumerateDevices();
+    availableMicrophones = devices.filter(device => device.kind === 'audioinput');
+
+    populateMicrophoneSelect();
+    console.log(`Found ${availableMicrophones.length} microphone(s)`);
+  } catch (error) {
+    console.error('Error enumerating microphones:', error);
+    statusText.textContent = "Error accessing microphones. Please grant permission.";
+  }
+}
+
+function populateMicrophoneSelect() {
+  if (!microphoneSelect) return;
+
+  microphoneSelect.innerHTML = '<option value="">Default Microphone</option>';
+
+  availableMicrophones.forEach((device, index) => {
+    const option = document.createElement('option');
+    option.value = device.deviceId;
+    option.textContent = device.label || `Microphone ${index + 1}`;
+    microphoneSelect.appendChild(option);
+  });
+
+  const savedMicId = localStorage.getItem('selectedMicrophone');
+  if (savedMicId && availableMicrophones.some(mic => mic.deviceId === savedMicId)) {
+    microphoneSelect.value = savedMicId;
+    selectedMicrophoneId = savedMicId;
+  }
+}
+
+function handleMicrophoneChange() {
+  selectedMicrophoneId = microphoneSelect.value || null;
+  localStorage.setItem('selectedMicrophone', selectedMicrophoneId || '');
+
+  const selectedDevice = availableMicrophones.find(mic => mic.deviceId === selectedMicrophoneId);
+  const deviceName = selectedDevice ? selectedDevice.label : 'Default Microphone';
+
+  console.log(`Selected microphone: ${deviceName}`);
+  statusText.textContent = `Microphone changed to: ${deviceName}`;
+
+  if (isRecording) {
+    statusText.textContent = "Switching microphone... Please wait.";
+    stopRecording().then(() => {
+      setTimeout(() => {
+        toggleRecording();
+      }, 1000);
+    });
+  }
+}
+
+// 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 = websocketUrl;
+
+// 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, start: it.start, 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.start !== undefined && item.end !== undefined) {
+        timeInfo = ` ${item.start} - ${item.end}`;
+      }
+
+      let speakerLabel = "";
+      if (item.speaker === -2) {
+        speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${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>Lag <span id='timeInfo'><span class="lag-transcription-value">${fmt1(
+              remaining_time_transcription
+            )}</span>s</span></span>`;
+          }
+          if (buffer_diarization && remaining_time_diarization > 0) {
+            speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Lag<span id='timeInfo'><span class="lag-diarization-value">${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.");
+    }
+
+    let stream;
+    try {
+      // Try tab capture first
+      stream = await new Promise((resolve, reject) => {
+        chrome.tabCapture.capture({audio: true}, (s) => {
+          if (s) {
+            resolve(s);
+          } else {
+            reject(new Error('Tab capture failed or not available'));
+          }
+        });
+      });
+      statusText.textContent = "Using tab audio capture.";
+    } catch (tabError) {
+      console.log('Tab capture not available, falling back to microphone', tabError);
+      // Fallback to microphone
+      const audioConstraints = selectedMicrophoneId
+        ? { audio: { deviceId: { exact: selectedMicrophoneId } } }
+        : { audio: true };
+      stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
+      statusText.textContent = "Using microphone audio.";
+    }
+
+    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 audio input. Browsers may block audio access on 0.0.0.0. Try using localhost:8000 instead.";
+    } else {
+      statusText.textContent = "Error accessing audio input. Please check permissions.";
+    }
+    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);
+
+if (microphoneSelect) {
+  microphoneSelect.addEventListener("change", handleMicrophoneChange);
+}
+
+// Settings toggle functionality
+settingsToggle.addEventListener("click", () => {
+  settingsDiv.classList.toggle("visible");
+  settingsToggle.classList.toggle("active");
+});
+
+document.addEventListener('DOMContentLoaded', async () => {
+  try {
+    await enumerateMicrophones();
+  } catch (error) {
+    console.log("Could not enumerate microphones on load:", error);
+  }
+});
+navigator.mediaDevices.addEventListener('devicechange', async () => {
+  console.log('Device change detected, re-enumerating microphones');
+  try {
+    await enumerateMicrophones();
+  } catch (error) {
+    console.log("Error re-enumerating microphones:", error);
+  }
+});
+
+
+async function run() {
+  const micPermission = await navigator.permissions.query({
+    name: "microphone",
+  });
+
+  document.getElementById(
+    "audioPermission"
+  ).innerText = `MICROPHONE: ${micPermission.state}`;
+
+  if (micPermission.state !== "granted") {
+    chrome.tabs.create({ url: "welcome.html" });
+  }
+
+  const intervalId = setInterval(async () => {
+    const micPermission = await navigator.permissions.query({
+      name: "microphone",
+    });
+    if (micPermission.state === "granted") {
+      document.getElementById(
+        "audioPermission"
+      ).innerText = `MICROPHONE: ${micPermission.state}`;
+      clearInterval(intervalId);
+    }
+  }, 100);
+}
+
+void run();
--- a/chrome-extension/manifest.json
+++ b/chrome-extension/manifest.json
@@ -0,0 +1,37 @@
+{
+    "manifest_version": 3,
+    "name": "WhisperLiveKit Tab Capture",
+    "version": "1.0",
+    "description": "Capture and transcribe audio from browser tabs using WhisperLiveKit.",
+    "background": {
+        "service_worker": "background.js"
+    },
+    "icons": {
+        "16": "icons/icon16.png",
+        "32": "icons/icon32.png",
+        "48": "icons/icon48.png",
+        "128": "icons/icon128.png"
+    },
+    "action": {
+        "default_title": "WhisperLiveKit Tab Capture",
+        "default_popup": "popup.html"
+    },
+    "permissions": [
+        "scripting",
+        "tabCapture",
+        "offscreen",
+        "activeTab",
+        "storage"
+    ],
+    "web_accessible_resources": [
+        {
+            "resources": [
+                "requestPermissions.html",
+                "requestPermissions.js"
+            ],
+            "matches": [
+                "<all_urls>"
+            ]
+        }
+    ]
+}
--- a/chrome-extension/popup.html
+++ b/chrome-extension/popup.html
@@ -0,0 +1,78 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <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>
+
+        <button id="settingsToggle" class="settings-toggle" title="Show/hide settings">
+            <img src="/web/src/settings.svg" alt="Settings" />
+        </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 class="field">
+                <label id="microphoneSelectLabel" for="microphoneSelect">Select Microphone</label>
+                <select id="microphoneSelect">
+                    <option value="">Default Microphone</option>
+                </select>
+                        <div id="audioPermission"></div>
+
+            </div>
+
+            <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>
+
+                    <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>
+
+                    <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>
+
+        </div>
+    </div>
+
+
+
+    <p id="status"></p>
+
+    <div id="linesTranscript"></div>
+
+    <script src="live_transcription.js"></script>
+</body>
+
+</html>
--- a/chrome-extension/requestPermissions.html
+++ b/chrome-extension/requestPermissions.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Request Permissions</title>
+    <script src="requestPermissions.js"></script>
+  </head>
+  <body>
+    This page exists to workaround an issue with Chrome that blocks permission
+    requests from chrome extensions
+    <button id="requestMicrophone">Request Microphone</button>
+  </body>
+</html>
--- a/chrome-extension/requestPermissions.js
+++ b/chrome-extension/requestPermissions.js
@@ -0,0 +1,17 @@
+/**
+ * Requests user permission for microphone access.
+ * @returns {Promise<void>} A Promise that resolves when permission is granted or rejects with an error.
+ */
+async function getUserPermission() {
+  console.log("Getting user permission for microphone access...");
+  await navigator.mediaDevices.getUserMedia({ audio: true });
+  const micPermission = await navigator.permissions.query({
+    name: "microphone",
+  });
+  if (micPermission.state == "granted") {
+    window.close();
+  }
+}
+
+// Call the function to request microphone permission
+getUserPermission();
--- a/chrome-extension/sidepanel.js
+++ b/chrome-extension/sidepanel.js
@@ -0,0 +1,29 @@
+console.log("sidepanel.js");
+
+async function run() {
+  const micPermission = await navigator.permissions.query({
+    name: "microphone",
+  });
+
+  document.getElementById(
+    "audioPermission"
+  ).innerText = `MICROPHONE: ${micPermission.state}`;
+
+  if (micPermission.state !== "granted") {
+    chrome.tabs.create({ url: "requestPermissions.html" });
+  }
+
+  const intervalId = setInterval(async () => {
+    const micPermission = await navigator.permissions.query({
+      name: "microphone",
+    });
+    if (micPermission.state === "granted") {
+      document.getElementById(
+        "audioPermission"
+      ).innerText = `MICROPHONE: ${micPermission.state}`;
+      clearInterval(intervalId);
+    }
+  }, 100);
+}
+
+void run();
--- a/chrome-extension/web/live_transcription.css
+++ b/chrome-extension/web/live_transcription.css
@@ -0,0 +1,539 @@
+: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);
+}
+
+.settings-toggle {
+  margin-top: 4px;
+  width: 40px;
+  height: 40px;
+  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;
+}
+
+.settings-toggle:hover {
+  background-color: var(--chip-bg);
+}
+
+.settings-toggle img {
+  width: 24px;
+  height: 24px;
+  opacity: 0.7;
+  transition: opacity 0.2s ease, transform 0.3s ease;
+}
+
+.settings-toggle:hover img {
+  opacity: 1;
+}
+
+.settings-toggle.active img {
+  transform: rotate(80deg);
+}
+
+/* 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: flex-start;
+  gap: 15px;
+  margin-top: 20px;
+  flex-wrap: wrap;
+}
+
+.settings {
+  display: none;
+  flex-wrap: wrap;
+  align-items: flex-start;
+  gap: 12px;
+  transition: opacity 0.3s ease;
+}
+
+.settings.visible {
+  display: flex;
+}
+
+.field {
+  display: flex;
+  flex-direction: column;
+  align-items: flex-start;
+  gap: 3px;
+}
+
+#chunkSelector,
+#websocketInput,
+#themeSelector,
+#microphoneSelect {
+  font-size: 16px;
+  padding: 5px 8px;
+  border-radius: 8px;
+  border: 1px solid var(--border);
+  background-color: var(--button-bg);
+  color: var(--text);
+  max-height: 30px;
+}
+
+#microphoneSelect {
+  width: 100%;
+  max-width: 190px;
+  min-width: 120px;
+}
+
+#chunkSelector:focus,
+#websocketInput:focus,
+#themeSelector:focus,
+#microphoneSelect: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 {
+  display: flex;
+  align-items: center;
+  margin-top: 17px;
+}
+
+.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;
+}
+
+/* for smaller screens */
+/* @media (max-width: 450px) {
+  .settings-container {
+    flex-direction: column;
+    gap: 10px;
+    align-items: center;
+  }
+
+  .settings {
+    justify-content: center;
+    gap: 8px;
+    width: 100%;
+  }
+
+  .field {
+    align-items: center;
+    width: 100%;
+  }
+
+  #websocketInput,
+  #microphoneSelect {
+    min-width: 200px;
+    max-width: 100%;
+  }
+
+  .theme-selector-container {
+    margin-top: 10px;
+  }
+} */
+
+/* @media (max-width: 768px) and (min-width: 451px) {
+  .settings-container {
+    gap: 10px;
+  }
+
+  .settings {
+    gap: 8px;
+  }
+
+  #websocketInput,
+  #microphoneSelect {
+    min-width: 150px;
+    max-width: 300px;
+  }
+} */
+
+/* @media (max-width: 480px) {
+  body {
+    margin: 10px;
+  }
+
+  .settings-toggle {
+    width: 35px;
+    height: 35px;
+  }
+
+  .settings-toggle img {
+    width: 20px;
+    height: 20px;
+  }
+
+  .settings {
+    flex-direction: column;
+    align-items: center;
+    gap: 6px;
+  }
+
+  #websocketInput,
+  #microphoneSelect {
+    max-width: 400px;
+  }
+
+  .segmented label {
+    padding: 4px 8px;
+    font-size: 12px;
+  }
+
+  .segmented img {
+    width: 14px;
+    height: 14px;
+  }
+} */
+
+
+html
+{
+    width: 400px;  /* max: 800px */
+    height: 600px; /* max: 600px */
+    border-radius: 10px;
+
+}
--- a/chrome-extension/web/src/dark_mode.svg
+++ b/chrome-extension/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>
--- a/chrome-extension/web/src/light_mode.svg
+++ b/chrome-extension/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>
--- a/chrome-extension/web/src/settings.svg
+++ b/chrome-extension/web/src/settings.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="M433-80q-27 0-46.5-18T363-142l-9-66q-13-5-24.5-12T307-235l-62 26q-25 11-50 2t-39-32l-47-82q-14-23-8-49t27-43l53-40q-1-7-1-13.5v-27q0-6.5 1-13.5l-53-40q-21-17-27-43t8-49l47-82q14-23 39-32t50 2l62 26q11-8 23-15t24-12l9-66q4-26 23.5-44t46.5-18h94q27 0 46.5 18t23.5 44l9 66q13 5 24.5 12t22.5 15l62-26q25-11 50-2t39 32l47 82q14 23 8 49t-27 43l-53 40q1 7 1 13.5v27q0 6.5-2 13.5l53 40q21 17 27 43t-8 49l-48 82q-14 23-39 32t-50-2l-60-26q-11 8-23 15t-24 12l-9 66q-4 26-23.5 44T527-80h-94Zm7-80h79l14-106q31-8 57.5-23.5T639-327l99 41 39-68-86-65q5-14 7-29.5t2-31.5q0-16-2-31.5t-7-29.5l86-65-39-68-99 42q-22-23-48.5-38.5T533-694l-13-106h-79l-14 106q-31 8-57.5 23.5T321-633l-99-41-39 68 86 64q-5 15-7 30t-2 32q0 16 2 31t7 30l-86 65 39 68 99-42q22 23 48.5 38.5T427-266l13 106Zm42-180q58 0 99-41t41-99q0-58-41-99t-99-41q-59 0-99.5 41T342-480q0 58 40.5 99t99.5 41Zm-2-140Z"/></svg>
--- a/chrome-extension/web/src/system_mode.svg
+++ b/chrome-extension/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>
--- a/chrome-extension/welcome.html
+++ b/chrome-extension/welcome.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Welcome</title>
+    <script src="welcome.js"></script>
+  </head>
+  <body>
+    This page exists to workaround an issue with Chrome that blocks permission
+    requests from chrome extensions
+    <!-- <button id="requestMicrophone">Request Microphone</button> -->
+  </body>
+</html>
--- a/demo.png
+++ b/demo.png
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,8 +4,8 @@ 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"
+version = "0.2.9"
+description = "Real-time speech-to-text with speaker diarization using Whisper"
 readme = "README.md"
 authors = [
    { name = "Quentin Fuxa" }
@@ -18,6 +18,11 @@ classifiers = [
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: 3.15",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Multimedia :: Sound/Audio :: Speech"
 ]
@@ -28,7 +33,8 @@ dependencies = [
    "faster-whisper",
    "uvicorn",
    "websockets",
-    "torch",
+    "torchaudio>=2.0.0",
+    "torch>=2.0.0",
    "tqdm",
    "tiktoken",
    'triton>=2.0.0; platform_machine == "x86_64" and (sys_platform == "linux" or sys_platform == "linux2")'
--- a/whisperlivekit/init.py
+++ b/whisperlivekit/init.py
@@ -1,12 +1,13 @@
 from .audio_processor import AudioProcessor
 from .core import TranscriptionEngine
 from .parse_args import parse_args
-from .web.web_interface import get_web_interface_html
+from .web.web_interface import get_web_interface_html, get_inline_ui_html

 __all__ = [
    "TranscriptionEngine",
    "AudioProcessor",
    "parse_args",
    "get_web_interface_html",
+    "get_inline_ui_html",
    "download_simulstreaming_backend",
 ]
--- a/whisperlivekit/audio_processor.py
+++ b/whisperlivekit/audio_processor.py
@@ -4,11 +4,11 @@ from time import time, sleep
 import math
 import logging
 import traceback
-from whisperlivekit.timed_objects import ASRToken, Silence
-from whisperlivekit.core import TranscriptionEngine, online_factory, online_diarization_factory
+from whisperlivekit.timed_objects import ASRToken, Silence, Line
+from whisperlivekit.core import TranscriptionEngine, online_factory, online_diarization_factory, online_translation_factory
 from whisperlivekit.ffmpeg_manager import FFmpegManager, FFmpegState
 from whisperlivekit.silero_vad_iterator import FixedVADIterator
-from whisperlivekit.results_formater import format_output, format_time
+from whisperlivekit.results_formater import format_output
 # Set up logging once
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
@@ -16,6 +16,17 @@ logger.setLevel(logging.DEBUG)

 SENTINEL = object() # unique sentinel object for end of stream marker

+
+async def get_all_from_queue(queue):
+    items = []
+    try:
+        while True:
+            item = queue.get_nowait()
+            items.append(item)
+    except asyncio.QueueEmpty:
+        pass
+    return items
+
 class AudioProcessor:
    """
    Processes audio streams for transcription and diarization.
@@ -41,6 +52,7 @@ class AudioProcessor:
        self.last_ffmpeg_activity = time()
        self.ffmpeg_health_check_interval = 5
        self.ffmpeg_max_idle_time = 10
+        self.is_pcm_input = self.args.pcm_input
        self.debug = False

        # State management
@@ -48,6 +60,7 @@ class AudioProcessor:
        self.silence = False
        self.silence_duration = 0.0
        self.tokens = []
+        self.translated_segments = []
        self.buffer_transcription = ""
        self.buffer_diarization = ""
        self.end_buffer = 0
@@ -80,23 +93,21 @@ class AudioProcessor:
        
        self.transcription_queue = asyncio.Queue() if self.args.transcription else None
        self.diarization_queue = asyncio.Queue() if self.args.diarization else None
+        self.translation_queue = asyncio.Queue() if self.args.target_language else None
        self.pcm_buffer = bytearray()

-        # Task references
        self.transcription_task = None
        self.diarization_task = None
        self.ffmpeg_reader_task = None
        self.watchdog_task = None
        self.all_tasks_for_cleanup = []
        
-        # Initialize transcription engine if enabled
        if self.args.transcription:
-            self.online = online_factory(self.args, models.asr, models.tokenizer)
-            
-        # Initialize diarization engine if enabled
+            self.online = online_factory(self.args, models.asr, models.tokenizer)            
        if self.args.diarization:
            self.diarization = online_diarization_factory(self.args, models.diarization_model)
-
+        if self.args.target_language:
+            self.online_translation = online_translation_factory(self.args, models.translation_model)

    def convert_pcm_to_float(self, pcm_buffer):
        """Convert PCM buffer in s16le format to normalized NumPy array."""
@@ -143,6 +154,7 @@ class AudioProcessor:
                
            return {
                "tokens": self.tokens.copy(),
+                "translated_segments": self.translated_segments.copy(),
                "buffer_transcription": self.buffer_transcription,
                "buffer_diarization": self.buffer_diarization,
                "end_buffer": self.end_buffer,
@@ -156,6 +168,7 @@ class AudioProcessor:
        """Reset all state variables to initial values."""
        async with self.lock:
            self.tokens = []
+            self.translated_segments = []
            self.buffer_transcription = self.buffer_diarization = ""
            self.end_buffer = self.end_attributed_speaker = 0
            self.beg_loop = time()
@@ -196,54 +209,7 @@ class AudioProcessor:
                        continue
                    
                self.pcm_buffer.extend(chunk)
-
-                # Process when enough data
-                if len(self.pcm_buffer) >= self.bytes_per_sec:
-                    if len(self.pcm_buffer) > self.max_bytes_per_sec:
-                        logger.warning(
-                            f"Audio buffer too large: {len(self.pcm_buffer) / self.bytes_per_sec:.2f}s. "
-                            f"Consider using a smaller model."
-                        )
-
-                    # Process audio chunk
-                    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:]
-                    
-                    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)
-
-                    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)
+                await self.handle_pcm_data()
                    
                    
                    
@@ -264,6 +230,8 @@ class AudioProcessor:
        if self.args.diarization and self.diarization_queue:
            await self.diarization_queue.put(SENTINEL)
            logger.debug("Sentinel put into diarization_queue.")
+        if self.args.target_language and self.translation_queue:
+            await self.translation_queue.put(SENTINEL)


    async def transcription_processor(self):
@@ -307,9 +275,6 @@ class AudioProcessor:
                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()
                
@@ -337,6 +302,11 @@ class AudioProcessor:
                await self.update_transcription(
                    new_tokens, buffer_text, new_end_buffer, self.sep
                )
+                
+                if new_tokens and self.args.target_language and self.translation_queue:
+                    for token in new_tokens:
+                        await self.translation_queue.put(token)
+                        
                self.transcription_queue.task_done()
                
            except Exception as e:
@@ -391,6 +361,49 @@ class AudioProcessor:
                    self.diarization_queue.task_done()
        logger.info("Diarization processor task finished.")

+    async def translation_processor(self, online_translation):
+        # the idea is to ignore diarization for the moment. We use only transcription tokens. 
+        # And the speaker is attributed given the segments used for the translation
+        # in the future we want to have different languages for each speaker etc, so it will be more complex.
+        while True:
+            try:
+                token = await self.translation_queue.get() #block until at least 1 token
+                if token is SENTINEL:
+                    logger.debug("Translation processor received sentinel. Finishing.")
+                    self.translation_queue.task_done()
+                    break
+                
+                # get all the available tokens for translation. The more words, the more precise
+                tokens_to_process = [token]
+                additional_tokens = await get_all_from_queue(self.translation_queue)
+                
+                sentinel_found = False
+                for additional_token in additional_tokens:
+                    if additional_token is SENTINEL:
+                        sentinel_found = True
+                        break
+                    tokens_to_process.append(additional_token)                
+                if tokens_to_process:
+                    online_translation.insert_tokens(tokens_to_process)
+                    self.translated_segments = online_translation.process()
+                
+                self.translation_queue.task_done()
+                for _ in additional_tokens:
+                    self.translation_queue.task_done()
+                
+                if sentinel_found:
+                    logger.debug("Translation processor received sentinel in batch. Finishing.")
+                    break
+                
+            except Exception as e:
+                logger.warning(f"Exception in translation_processor: {e}")
+                logger.warning(f"Traceback: {traceback.format_exc()}")
+                if 'token' in locals() and token is not SENTINEL:
+                    self.translation_queue.task_done()
+                if 'additional_tokens' in locals():
+                    for _ in additional_tokens:
+                        self.translation_queue.task_done()
+        logger.info("Translation processor task finished.")

    async def results_formatter(self):
        """Format processing results for output."""
@@ -433,7 +446,7 @@ class AudioProcessor:
                    state,
                    self.silence,
                    current_time = time() - self.beg_loop if self.beg_loop else None,
-                    diarization = self.args.diarization,
+                    args = self.args,
                    debug = self.debug
                )
                # Handle undiarized text
@@ -445,23 +458,19 @@ class AudioProcessor:
                    buffer_diarization = combined
                
                response_status = "active_transcription"
-                final_lines_for_response = lines.copy()
-
                if not tokens and not buffer_transcription and not buffer_diarization:
                    response_status = "no_audio_detected"
-                    final_lines_for_response = []
-                elif response_status == "active_transcription" and not final_lines_for_response:
-                    final_lines_for_response = [{
-                        "speaker": 1,
-                        "text": "",
-                        "beg": format_time(state.get("end_buffer", 0)),
-                        "end": format_time(state.get("end_buffer", 0)),
-                        "diff": 0
-                    }]
+                    lines = []
+                elif response_status == "active_transcription" and not lines:
+                    lines = [Line(
+                        speaker=1,
+                        start=state.get("end_buffer", 0),
+                        end=state.get("end_buffer", 0)        
+                    )]
                
                response = {
                    "status": response_status,
-                    "lines": final_lines_for_response,
+                    "lines": [line.to_dict() for line in lines],
                    "buffer_transcription": buffer_transcription,
                    "buffer_diarization": buffer_diarization,
                    "remaining_time_transcription": state["remaining_time_transcription"],
@@ -469,7 +478,7 @@ class AudioProcessor:
                }
                
                current_response_signature = f"{response_status} | " + \
-                                           ' '.join([f"{line['speaker']} {line['text']}" for line in final_lines_for_response]) + \
+                                           ' '.join([f"{line.speaker} {line.text}" for line in lines]) + \
                                           f" | {buffer_transcription} | {buffer_diarization}"
                
                trans = state["remaining_time_transcription"]
@@ -480,7 +489,7 @@ class AudioProcessor:
                    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):
+                if should_push and (lines 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
@@ -496,7 +505,6 @@ class AudioProcessor:
                    
                    if all_processors_done:
                        logger.info("Results formatter: All upstream processors are done and in stopping state. Terminating.")
-                        final_state = await self.get_current_state()
                        return
                
                await asyncio.sleep(0.1)  # Avoid overwhelming the client
@@ -536,6 +544,11 @@ class AudioProcessor:
            self.all_tasks_for_cleanup.append(self.diarization_task)
            processing_tasks_for_watchdog.append(self.diarization_task)
        
+        if self.args.target_language and self.args.lan != 'auto':
+            self.translation_task = asyncio.create_task(self.translation_processor(self.online_translation))
+            self.all_tasks_for_cleanup.append(self.translation_task)
+            processing_tasks_for_watchdog.append(self.translation_task)
+        
        self.ffmpeg_reader_task = asyncio.create_task(self.ffmpeg_stdout_reader())
        self.all_tasks_for_cleanup.append(self.ffmpeg_reader_task)
        processing_tasks_for_watchdog.append(self.ffmpeg_reader_task)
@@ -578,20 +591,21 @@ class AudioProcessor:
        
    async def cleanup(self):
        """Clean up resources when processing is complete."""
-        logger.info("Starting cleanup of AudioProcessor resources.")        
+        logger.info("Starting cleanup of AudioProcessor resources.")
+        self.is_stopping = True
        for task in self.all_tasks_for_cleanup:
            if task and not task.done():
                task.cancel()
-        
-        created_tasks = [t for t in self.all_tasks_for_cleanup if t]
-        if created_tasks:
-            await asyncio.gather(*created_tasks, return_exceptions=True)
-        logger.info("All processing tasks cancelled or finished.")
-        await self.ffmpeg_manager.stop()
-        logger.info("FFmpeg manager stopped.")
-        if self.args.diarization and hasattr(self, 'diarization') and hasattr(self.diarization, 'close'):
-            self.diarization.close()
-        logger.info("AudioProcessor cleanup complete.")
+            
+            created_tasks = [t for t in self.all_tasks_for_cleanup if t]
+            if created_tasks:
+                await asyncio.gather(*created_tasks, return_exceptions=True)
+            logger.info("All processing tasks cancelled or finished.")
+            await self.ffmpeg_manager.stop()
+            logger.info("FFmpeg manager stopped.")
+            if self.args.diarization and hasattr(self, 'diarization') and hasattr(self.diarization, 'close'):
+                self.diarization.close()
+            logger.info("AudioProcessor cleanup complete.")


    async def process_audio(self, message):
@@ -611,10 +625,65 @@ class AudioProcessor:
            logger.warning("AudioProcessor is stopping. Ignoring incoming audio.")
            return

-        success = await self.ffmpeg_manager.write_data(message)
-        if not success:
-            ffmpeg_state = await self.ffmpeg_manager.get_state()
-            if ffmpeg_state == FFmpegState.FAILED:
-                logger.error("FFmpeg is in FAILED state, cannot process audio")
-            else:
-                logger.warning("Failed to write audio data to FFmpeg")
+        if self.is_pcm_input:
+            self.pcm_buffer.extend(message)
+            await self.handle_pcm_data()
+        else:
+            success = await self.ffmpeg_manager.write_data(message)
+            if not success:
+                ffmpeg_state = await self.ffmpeg_manager.get_state()
+                if ffmpeg_state == FFmpegState.FAILED:
+                    logger.error("FFmpeg is in FAILED state, cannot process audio")
+                else:
+                    logger.warning("Failed to write audio data to FFmpeg")
+
+    async def handle_pcm_data(self):
+        # Process when enough data
+        if len(self.pcm_buffer) < self.bytes_per_sec:
+            return
+
+        if len(self.pcm_buffer) > self.max_bytes_per_sec:
+            logger.warning(
+                f"Audio buffer too large: {len(self.pcm_buffer) / self.bytes_per_sec:.2f}s. "
+                f"Consider using a smaller model."
+            )
+
+        # Process audio chunk
+        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:]
+
+        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)
+
+        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()
+
+        if not self.args.transcription and not self.args.diarization:
+            await asyncio.sleep(0.1)
--- a/whisperlivekit/basic_server.py
+++ b/whisperlivekit/basic_server.py
@@ -2,7 +2,7 @@ from contextlib import asynccontextmanager
 from fastapi import FastAPI, WebSocket, WebSocketDisconnect
 from fastapi.responses import HTMLResponse
 from fastapi.middleware.cors import CORSMiddleware
-from whisperlivekit import TranscriptionEngine, AudioProcessor, get_web_interface_html, parse_args
+from whisperlivekit import TranscriptionEngine, AudioProcessor, get_inline_ui_html, parse_args
 import asyncio
 import logging
 from starlette.staticfiles import StaticFiles
@@ -19,6 +19,15 @@ transcription_engine = None

@asynccontextmanager
 async def lifespan(app: FastAPI):
+    
+    #to remove after 0.2.8
+    if args.backend == "simulstreaming" and not args.disable_fast_encoder:
+        logger.warning(f"""
+{'='*50}
+WhisperLiveKit 0.2.8 has introduced a new fast encoder feature using MLX Whisper or Faster Whisper for improved speed. Use --disable-fast-encoder to disable if you encounter issues.
+{'='*50}
+    """)
+    
    global transcription_engine
    transcription_engine = TranscriptionEngine(
        **vars(args),
@@ -38,7 +47,7 @@ app.mount("/web", StaticFiles(directory=str(web_dir)), name="web")

@app.get("/")
 async def get():
-    return HTMLResponse(get_web_interface_html())
+    return HTMLResponse(get_inline_ui_html())


 async def handle_websocket_results(websocket, results_generator):
--- a/whisperlivekit/core.py
+++ b/whisperlivekit/core.py
@@ -33,6 +33,7 @@ class TranscriptionEngine:
            "model_dir": None,
            "lan": "auto",
            "task": "transcribe",
+            "target_language": "",
            "backend": "faster-whisper",
            "vac": True,
            "vac_chunk_size": 0.04,
@@ -41,11 +42,13 @@ class TranscriptionEngine:
            "ssl_keyfile": None,
            "transcription": True,
            "vad": True,
+            "pcm_input": False,
            # whisperstreaming params:
            "buffer_trimming": "segment",
            "confidence_validation": False,
            "buffer_trimming_sec": 15,
            # simulstreaming params:
+            "disable_fast_encoder": False,
            "frame_threshold": 25,
            "beams": 1,
            "decoder_type": None,
@@ -58,9 +61,10 @@ class TranscriptionEngine:
            "max_context_tokens": None,
            "model_path": './base.pt',
            "diarization_backend": "sortformer",
-            # diart params:
+            # diarization params:
+            "disable_punctuation_split" : False,
            "segmentation_model": "pyannote/segmentation-3.0",
-            "embedding_model": "pyannote/embedding",
+            "embedding_model": "pyannote/embedding",         
        }

        config_dict = {**defaults, **kwargs}
@@ -97,7 +101,7 @@ class TranscriptionEngine:
                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']:
+                            'max_context_tokens', 'model_path', 'warmup_file', 'preload_model_count', 'disable_fast_encoder']:
                    if hasattr(self.args, attr):
                        simulstreaming_kwargs[attr] = getattr(self.args, attr)
        
@@ -131,6 +135,14 @@ class TranscriptionEngine:
                self.diarization_model = SortformerDiarization()
            else:
                raise ValueError(f"Unknown diarization backend: {self.args.diarization_backend}")
+        
+        self.translation_model = None
+        if self.args.target_language:
+            if self.args.lan == 'auto':
+                raise Exception('Translation cannot be set with language auto')
+            else:
+                from whisperlivekit.translation.translation import load_model
+                self.translation_model = load_model([self.args.lan]) #in the future we want to handle different languages for different speakers
            
        TranscriptionEngine._initialized = True

@@ -158,11 +170,17 @@ def online_factory(args, asr, tokenizer, logfile=sys.stderr):
 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
+        # Not the best here, since several user/instances will share the same backend, but diart is not SOTA anymore and sortformer is recommended
    
    if args.diarization_backend == "sortformer":
        from whisperlivekit.diarization.sortformer_backend import SortformerDiarizationOnline
        online = SortformerDiarizationOnline(shared_model=diarization_backend)
    return online

-        
+
+def online_translation_factory(args, translation_model):
+    #should be at speaker level in the future:
+    #one shared nllb model for all speaker
+    #one tokenizer per speaker/language
+    from whisperlivekit.translation.translation import OnlineTranslation
+    return OnlineTranslation(translation_model, [args.lan], [args.target_language])
--- a/whisperlivekit/diarization/sortformer_backend.py
+++ b/whisperlivekit/diarization/sortformer_backend.py
@@ -60,11 +60,15 @@ class SortformerDiarization:
            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")
+            device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+            self.diar_model.to(device)
+            
+            ## to test
+            # for name, param in self.diar_model.named_parameters():
+            #     if param.device != device:
+            #         raise RuntimeError(f"Parameter {name} is on {param.device} but should be on {device}")
+            
+            logger.info(f"Using {device.type.upper()} for Sortformer model")

            self.diar_model.sortformer_modules.chunk_len = 10
            self.diar_model.sortformer_modules.subsampling_factor = 10
@@ -106,6 +110,7 @@ class SortformerDiarizationOnline:
            features=128,
            pad_to=0
        )
+        self.audio2mel.to(self.diar_model.device)
        
        self.chunk_duration_seconds = (
            self.diar_model.sortformer_modules.chunk_len * 
@@ -186,22 +191,25 @@ class SortformerDiarizationOnline:
            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)
+            device = self.diar_model.device
+            audio_signal_chunk = torch.tensor(audio, device=device).unsqueeze(0)
+            audio_signal_length_chunk = torch.tensor([audio_signal_chunk.shape[1]], device=device)
            
            processed_signal_chunk, processed_signal_length_chunk = self.audio2mel.get_features(
                audio_signal_chunk, audio_signal_length_chunk
            )
+            processed_signal_chunk = processed_signal_chunk.to(device)
+            processed_signal_length_chunk = processed_signal_length_chunk.to(device)
            
            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)
+                to_add = self._previous_chunk_features[:, :, -99:].to(device)
+                total_features = torch.concat([to_add, processed_signal_chunk], dim=2).to(device)
            else:
-                total_features = processed_signal_chunk
+                total_features = processed_signal_chunk.to(device)
            
-            self._previous_chunk_features = processed_signal_chunk
+            self._previous_chunk_features = processed_signal_chunk.to(device)
            
-            chunk_feat_seq_t = torch.transpose(total_features, 1, 2)
+            chunk_feat_seq_t = torch.transpose(total_features, 1, 2).to(device)
            
            with torch.inference_mode():
                left_offset = 8 if self._chunk_index > 0 else 0
@@ -209,7 +217,7 @@ class SortformerDiarizationOnline:
                
                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]]),
+                    processed_signal_length=torch.tensor([chunk_feat_seq_t.shape[1]]).to(device),
                    streaming_state=self.streaming_state,
                    total_preds=self.total_preds,
                    left_offset=left_offset,
--- a/whisperlivekit/parse_args.py
+++ b/whisperlivekit/parse_args.py
@@ -72,6 +72,12 @@ def parse_args():
        help="Disable transcription to only see live diarization results.",
    )
    
+    parser.add_argument(
+        "--disable-punctuation-split",
+        action="store_true",
+        help="Disable the split parameter.",
+    )
+    
    parser.add_argument(
        "--min-chunk-size",
        type=float,
@@ -112,6 +118,15 @@ def parse_args():
        choices=["transcribe", "translate"],
        help="Transcribe or translate.",
    )
+    
+    parser.add_argument(
+        "--target-language",
+        type=str,
+        default="",
+        dest="target_language",
+        help="Target language for translation. Not functional yet.",
+    )    
+
    parser.add_argument(
        "--backend",
        type=str,
@@ -158,9 +173,22 @@ def parse_args():
    )
    parser.add_argument("--ssl-certfile", type=str, help="Path to the SSL certificate file.", default=None)
    parser.add_argument("--ssl-keyfile", type=str, help="Path to the SSL private key file.", default=None)
-
+    parser.add_argument(
+        "--pcm-input",
+        action="store_true",
+        default=False,
+        help="If set, raw PCM (s16le) data is expected as input and FFmpeg will be bypassed."
+    )
    # SimulStreaming-specific arguments
    simulstreaming_group = parser.add_argument_group('SimulStreaming arguments (only used with --backend simulstreaming)')
+
+    simulstreaming_group.add_argument(
+        "--disable-fast-encoder",
+        action="store_true",
+        default=False,
+        dest="disable_fast_encoder",
+        help="Disable Faster Whisper or MLX Whisper backends for encoding (if installed). Slower but helpful when GPU memory is limited",
+    )
    
    simulstreaming_group.add_argument(
        "--frame-threshold",
@@ -252,10 +280,10 @@ def parse_args():
    )
    
    simulstreaming_group.add_argument(
-        "--preloaded_model_count",
+        "--preload-model-count",
        type=int,
        default=1,
-        dest="preloaded_model_count",
+        dest="preload_model_count",
        help="Optional. Number of models to preload in memory to speed up loading (set up to the expected number of concurrent instances).",
    )

--- a/whisperlivekit/results_formater.py
+++ b/whisperlivekit/results_formater.py
@@ -1,19 +1,14 @@

 import logging
-from datetime import timedelta
 from whisperlivekit.remove_silences import handle_silences
+from whisperlivekit.timed_objects import Line, format_time

 logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)

-PUNCTUATION_MARKS = {'.', '!', '?'}
+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
@@ -34,31 +29,28 @@ def next_speaker_change(i, tokens, 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)
-    }
+    return Line(
+        speaker = speaker,
+        text = token.text + debug_info,
+        start = token.start,
+        end = token.end,
+    )

-
-def append_token_to_last_line(lines, sep, token, debug_info, last_end_diarized):
+def append_token_to_last_line(lines, sep, token, debug_info):
    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)
-            
+        lines[-1].text += sep + token.text + debug_info
+        lines[-1].end = token.end

-def format_output(state, silence, current_time, diarization, debug):
+def format_output(state, silence, current_time, args, debug):
+    diarization = args.diarization
+    disable_punctuation_split = args.disable_punctuation_split
    tokens = state["tokens"]
+    translated_segments = state["translated_segments"] # Here we will attribute the speakers only based on the timestamps of the segments
    buffer_transcription = state["buffer_transcription"]
    buffer_diarization = state["buffer_diarization"]
    end_attributed_speaker = state["end_attributed_speaker"]
@@ -66,13 +58,11 @@ def format_output(state, silence, current_time, diarization, debug):
    
    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:
@@ -81,18 +71,15 @@ def format_output(state, silence, current_time, diarization, debug):
                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 = ""))
+            lines.append(new_line(token, speaker, debug_info = ""))
            continue
        else:
-            previous_speaker = lines[-1]['speaker']
+            previous_speaker = lines[-1].speaker
        
        if is_punctuation(token):
            last_punctuation = i
@@ -101,7 +88,7 @@ def format_output(state, silence, current_time, diarization, debug):
        if last_punctuation == i-1:
            if speaker != previous_speaker:
                # perfect, diarization perfectly aligned
-                lines.append(new_line(token, speaker, last_end_diarized, debug_info = ""))
+                lines.append(new_line(token, speaker, debug_info = ""))
                last_punctuation, next_punctuation = None, None
                continue
            
@@ -111,28 +98,40 @@ def format_output(state, silence, current_time, diarization, debug):
                # 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 = ""))
+                lines.append(new_line(token, new_speaker, debug_info = ""))
            else:
                # No speaker change to come
-                append_token_to_last_line(lines, sep, token, debug_info, last_end_diarized)
+                append_token_to_last_line(lines, sep, token, debug_info)
            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 = ""))
+                lines.append(new_line(token, speaker, 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)
+                append_token_to_last_line(lines, sep, token, debug_info)
                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 = ""))
+                if disable_punctuation_split:
+                    lines.append(new_line(token, speaker, debug_info = ""))
+                    continue
                pass
            
-        append_token_to_last_line(lines, sep, token, debug_info, last_end_diarized)
+        append_token_to_last_line(lines, sep, token, debug_info)
+    if lines and translated_segments:
+        cts_idx = 0 # current_translated_segment_idx
+        for line in lines:
+            while cts_idx < len(translated_segments):
+                ts = translated_segments[cts_idx]
+                if ts.start and ts.start >= line.start and ts.end <= line.end:
+                    line.translation += ts.text + ' '
+                    cts_idx += 1
+                else:
+                    break
    return lines, undiarized_text, buffer_transcription, '' 

--- a/whisperlivekit/simul_whisper/backend.py
+++ b/whisperlivekit/simul_whisper/backend.py
@@ -3,25 +3,37 @@ import numpy as np
 import logging
 from typing import List, Tuple, Optional
 import logging
+import platform
 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__)

+import torch
+from whisperlivekit.simul_whisper.config import AlignAttConfig
+from whisperlivekit.simul_whisper.simul_whisper import PaddedAlignAttWhisper
+from whisperlivekit.simul_whisper.whisper import tokenizer
+
 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]".""")
+    from .mlx_encoder import mlx_model_mapping, load_mlx_encoder
+    HAS_MLX_WHISPER = True
+except ImportError:
+    if platform.system() == "Darwin" and platform.machine() == "arm64":
+        print('MLX Whisper not found but you are on Apple Silicon. Consider installing mlx-whisper for better performance: pip install mlx-whisper')
+    HAS_MLX_WHISPER = False
+if HAS_MLX_WHISPER:
+    HAS_FASTER_WHISPER = False
+else:
+    try:
+        from faster_whisper import WhisperModel
+        HAS_FASTER_WHISPER = True
+    except ImportError:
+        HAS_FASTER_WHISPER = False
+

 # TOO_MANY_REPETITIONS = 3

@@ -51,7 +63,10 @@ class SimulStreamingOnlineProcessor:
        model = self.asr.get_new_model_instance()
        self.model = PaddedAlignAttWhisper(
            cfg=self.asr.cfg,
-            loaded_model=model)
+            loaded_model=model,
+            mlx_encoder=self.asr.mlx_encoder,
+            fw_encoder=self.asr.fw_encoder,
+            )

    def insert_silence(self, silence_duration, offset):
        """
@@ -64,7 +79,7 @@ class SimulStreamingOnlineProcessor:
        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
+            self.global_time_offset = silence_duration + offset


        
@@ -231,7 +246,8 @@ class SimulStreamingASR():
        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)
-        
+        self.disable_fast_encoder = kwargs.get('disable_fast_encoder', False)
+        self.fast_encoder = False
        if model_dir is not None:
            self.model_path = model_dir
        elif modelsize is not None:
@@ -276,15 +292,44 @@ class SimulStreamingASR():
        
        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)]
    
+        self.mlx_encoder, self.fw_encoder = None, None
+        if not self.disable_fast_encoder:
+            if HAS_MLX_WHISPER:
+                print('Simulstreaming will use MLX whisper for a faster encoder.')
+                mlx_model_name = mlx_model_mapping[self.model_name]
+                self.mlx_encoder = load_mlx_encoder(path_or_hf_repo=mlx_model_name)
+                self.fast_encoder = True
+            elif HAS_FASTER_WHISPER:
+                print('Simulstreaming will use Faster Whisper for the encoder.')
+                self.fw_encoder = WhisperModel(
+                    self.model_name,
+                    device='auto',
+                    compute_type='auto',
+                )
+                self.fast_encoder = True

+        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)
+        whisper_model = load_model(name=self.model_name, download_root=self.model_path, decoder_only=self.fast_encoder)
        warmup_audio = load_file(self.warmup_file)
-        whisper_model.transcribe(warmup_audio, language=self.original_language if self.original_language != 'auto' else None)
+        if warmup_audio is not None:
+            warmup_audio = torch.from_numpy(warmup_audio).float()
+            if self.fast_encoder:                
+                temp_model = PaddedAlignAttWhisper(
+                    cfg=self.cfg,
+                    loaded_model=whisper_model,
+                    mlx_encoder=self.mlx_encoder,
+                    fw_encoder=self.fw_encoder,
+                )
+                temp_model.warmup(warmup_audio)
+                temp_model.remove_hooks()
+            else:
+                # For standard encoder, use the original transcribe warmup
+                warmup_audio = load_file(self.warmup_file)
+                whisper_model.transcribe(warmup_audio, language=self.original_language if self.original_language != 'auto' else None)
        return whisper_model
    
    def get_new_model_instance(self):
--- a/whisperlivekit/simul_whisper/mlx_encoder.py
+++ b/whisperlivekit/simul_whisper/mlx_encoder.py
@@ -0,0 +1,72 @@
+import json
+from pathlib import Path
+
+import mlx.core as mx
+import mlx.nn as nn
+from huggingface_hub import snapshot_download
+from mlx.utils import tree_unflatten
+
+from mlx_whisper import whisper
+
+mlx_model_mapping = {
+    "tiny.en": "mlx-community/whisper-tiny.en-mlx",
+    "tiny": "mlx-community/whisper-tiny-mlx",
+    "base.en": "mlx-community/whisper-base.en-mlx",
+    "base": "mlx-community/whisper-base-mlx",
+    "small.en": "mlx-community/whisper-small.en-mlx",
+    "small": "mlx-community/whisper-small-mlx",
+    "medium.en": "mlx-community/whisper-medium.en-mlx",
+    "medium": "mlx-community/whisper-medium-mlx",
+    "large-v1": "mlx-community/whisper-large-v1-mlx",
+    "large-v2": "mlx-community/whisper-large-v2-mlx",
+    "large-v3": "mlx-community/whisper-large-v3-mlx",
+    "large-v3-turbo": "mlx-community/whisper-large-v3-turbo",
+    "large": "mlx-community/whisper-large-mlx",
+}
+
+def load_mlx_encoder(
+    path_or_hf_repo: str,
+    dtype: mx.Dtype = mx.float32,
+) -> whisper.Whisper:
+    model_path = Path(path_or_hf_repo)
+    if not model_path.exists():
+        model_path = Path(snapshot_download(repo_id=path_or_hf_repo))
+
+    with open(str(model_path / "config.json"), "r") as f:
+        config = json.loads(f.read())
+        config.pop("model_type", None)
+        quantization = config.pop("quantization", None)
+
+    model_args = whisper.ModelDimensions(**config)
+
+    wf = model_path / "weights.safetensors"
+    if not wf.exists():
+        wf = model_path / "weights.npz"
+    weights = mx.load(str(wf))
+
+    model = whisper.Whisper(model_args, dtype)
+
+    if quantization is not None:
+        class_predicate = (
+            lambda p, m: isinstance(m, (nn.Linear, nn.Embedding))
+            and f"{p}.scales" in weights
+        )
+        nn.quantize(model, **quantization, class_predicate=class_predicate)
+
+    weights = tree_unflatten(list(weights.items()))
+    
+    # we only want to load the encoder weights here.
+    # Size examples: for tiny.en, 
+    # Decoder weights: 59110771 bytes
+    # Encoder weights: 15268874 bytes
+
+    
+    encoder_weights = {}
+    encoder_weights['encoder'] = weights['encoder']
+    del(weights)
+    
+
+
+    model.update(encoder_weights)
+    mx.eval(model.parameters())
+    return model
--- a/whisperlivekit/simul_whisper/simul_whisper.py
+++ b/whisperlivekit/simul_whisper/simul_whisper.py
@@ -14,7 +14,7 @@ from .whisper.decoding import GreedyDecoder, BeamSearchDecoder, SuppressTokens,
 from .beam import BeamPyTorchInference
 from .eow_detection import fire_at_boundary, load_cif
 import os
-
+from time import time
 from .token_buffer import TokenBuffer

 import numpy as np
@@ -23,8 +23,22 @@ from .generation_progress import *
 DEC_PAD = 50257
 logger = logging.getLogger(__name__)

-import sys
-import wave
+
+try:
+    from mlx_whisper.audio import log_mel_spectrogram as mlx_log_mel_spectrogram
+    from mlx_whisper.transcribe import pad_or_trim as mlx_pad_or_trim
+    HAS_MLX_WHISPER = True
+except ImportError:
+    HAS_MLX_WHISPER = False
+if HAS_MLX_WHISPER:
+    HAS_FASTER_WHISPER = False
+else:
+    try:
+        from faster_whisper.audio import pad_or_trim as fw_pad_or_trim
+        from faster_whisper.feature_extractor import FeatureExtractor
+        HAS_FASTER_WHISPER = True
+    except ImportError:
+        HAS_FASTER_WHISPER = False

 # New features added to the original version of Simul-Whisper: 
 # - large-v3 model support
@@ -33,7 +47,13 @@ import wave
 # - prompt -- static vs. non-static
 # - context
 class PaddedAlignAttWhisper:
-    def __init__(self, cfg: AlignAttConfig, loaded_model=None) -> None:
+    def __init__(
+            self, 
+            cfg: AlignAttConfig,
+            loaded_model=None,
+            mlx_encoder=None,
+            fw_encoder=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))
@@ -41,7 +61,14 @@ class PaddedAlignAttWhisper:
            self.model = loaded_model
        else:
            self.model = load_model(name=model_name, download_root=model_path)
+        
+        self.device = 'cuda' if torch.cuda.is_available() else 'cpu'

+        self.mlx_encoder = mlx_encoder
+        self.fw_encoder = fw_encoder
+        if fw_encoder:
+            self.fw_feature_extractor = FeatureExtractor(feature_size=self.model.dims.n_mels)
+            
        logger.info(f"Model dimensions: {self.model.dims}")

        self.decode_options = DecodingOptions(
@@ -147,10 +174,18 @@ class PaddedAlignAttWhisper:
            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 warmup(self, audio):
+        try:
+            self.insert_audio(audio)
+            self.infer(is_last=True)
+            self.refresh_segment(complete=True)
+            logger.info("Model warmed up successfully")
+        except Exception as e:
+            logger.exception(f"Model warmup failed: {e}")
+
    def create_tokenizer(self, language=None):
        self.tokenizer = tokenizer.get_tokenizer(
            multilingual=self.tokenizer_is_multilingual,  
@@ -359,20 +394,38 @@ class PaddedAlignAttWhisper:
        else:
            input_segments = self.segments[0]

-
-        
-        # mel + padding to 30s
-        mel_padded = log_mel_spectrogram(input_segments, n_mels=self.model.dims.n_mels, padding=N_SAMPLES, 
-                                            device=self.model.device).unsqueeze(0)
-        # trim to 3000
-        mel = pad_or_trim(mel_padded, N_FRAMES)
-
-        # the len of actual audio
-        content_mel_len = int((mel_padded.shape[2] - mel.shape[2])/2)
-
-        # encode
-        encoder_feature = self.model.encoder(mel)
-
+        # NEW : we can use a different encoder, before using standart whisper for cross attention with the hooks on the decoder
+        beg_encode = time()
+        if self.mlx_encoder:
+            mlx_mel_padded = mlx_log_mel_spectrogram(audio=input_segments.detach(), n_mels=self.model.dims.n_mels, padding=N_SAMPLES)
+            mlx_mel = mlx_pad_or_trim(mlx_mel_padded, N_FRAMES, axis=-2)
+            mlx_encoder_feature = self.mlx_encoder.encoder(mlx_mel[None])
+            encoder_feature = torch.as_tensor(mlx_encoder_feature)
+            content_mel_len = int((mlx_mel_padded.shape[0] - mlx_mel.shape[0])/2)
+        elif self.fw_encoder:
+            audio_length_seconds = len(input_segments) / 16000   
+            content_mel_len = int(audio_length_seconds * 100)//2      
+            mel_padded_2 = self.fw_feature_extractor(waveform=input_segments.numpy(), padding=N_SAMPLES)[None, :]
+            mel = fw_pad_or_trim(mel_padded_2, N_FRAMES, axis=-1)
+            encoder_feature_ctranslate = self.fw_encoder.encode(mel)
+            if self.device == 'cpu': #it seems that on gpu, passing StorageView to torch.as_tensor fails and wrapping in the array works
+                encoder_feature_ctranslate = np.array(encoder_feature_ctranslate)
+            try:
+                encoder_feature = torch.as_tensor(encoder_feature_ctranslate, device=self.device)
+            except TypeError: # Normally the cpu condition should prevent having exceptions, but just in case:
+                encoder_feature = torch.as_tensor(np.array(encoder_feature_ctranslate), device=self.device)
+        else:
+            # mel + padding to 30s
+            mel_padded = log_mel_spectrogram(input_segments, n_mels=self.model.dims.n_mels, padding=N_SAMPLES, 
+                                                device=self.device).unsqueeze(0)
+            # trim to 3000
+            mel = pad_or_trim(mel_padded, N_FRAMES)
+            # the len of actual audio
+            content_mel_len = int((mel_padded.shape[2] - mel.shape[2])/2)
+            encoder_feature = self.model.encoder(mel)
+        end_encode = time()
+        # print('Encoder duration:', end_encode-beg_encode)
+                
 #        logger.debug(f"Encoder feature shape: {encoder_feature.shape}")
 #        if mel.shape[-2:] != (self.model.dims.n_audio_ctx, self.model.dims.n_audio_state):
 #            logger.debug("mel ")
@@ -397,7 +450,7 @@ class PaddedAlignAttWhisper:
        ####################### Decoding loop
        logger.info("Decoding loop starts\n")

-        sum_logprobs = torch.zeros(self.cfg.beam_size, device=mel.device)
+        sum_logprobs = torch.zeros(self.cfg.beam_size, device=self.device)
        completed = False

        attn_of_alignment_heads = None
@@ -608,7 +661,7 @@ class PaddedAlignAttWhisper:
        ### new hypothesis
        logger.debug(f"new_hypothesis: {new_hypothesis}")
        new_tokens = torch.tensor([new_hypothesis], dtype=torch.long).repeat_interleave(self.cfg.beam_size, dim=0).to(
-            device=self.model.device,
+            device=self.device,
        )
        self.tokens.append(new_tokens)
        # TODO: test if this is redundant or not
@@ -618,4 +671,4 @@ class PaddedAlignAttWhisper:
        
        self._clean_cache()

-        return new_hypothesis, generation
+        return new_hypothesis, generation
--- a/whisperlivekit/simul_whisper/whisper/init.py
+++ b/whisperlivekit/simul_whisper/whisper/init.py
@@ -105,6 +105,7 @@ def load_model(
    device: Optional[Union[str, torch.device]] = None,
    download_root: str = None,
    in_memory: bool = False,
+    decoder_only=False
 ) -> Whisper:
    """
    Load a Whisper ASR model
@@ -151,7 +152,14 @@ def load_model(
    del checkpoint_file

    dims = ModelDimensions(**checkpoint["dims"])
-    model = Whisper(dims)
+    model = Whisper(dims, decoder_only=decoder_only)
+    
+    if decoder_only:
+        checkpoint["model_state_dict"] = {
+            k: v for k, v in checkpoint["model_state_dict"].items() 
+            if 'encoder' not in k
+        }
+
    model.load_state_dict(checkpoint["model_state_dict"])

    if alignment_heads is not None:
--- a/whisperlivekit/simul_whisper/whisper/model.py
+++ b/whisperlivekit/simul_whisper/whisper/model.py
@@ -253,16 +253,18 @@ class TextDecoder(nn.Module):


 class Whisper(nn.Module):
-    def __init__(self, dims: ModelDimensions):
+    def __init__(self, dims: ModelDimensions, decoder_only: bool = False):
        super().__init__()
        self.dims = dims
-        self.encoder = AudioEncoder(
-            self.dims.n_mels,
-            self.dims.n_audio_ctx,
-            self.dims.n_audio_state,
-            self.dims.n_audio_head,
-            self.dims.n_audio_layer,
-        )
+        
+        if not decoder_only:
+            self.encoder = AudioEncoder(
+                self.dims.n_mels,
+                self.dims.n_audio_ctx,
+                self.dims.n_audio_state,
+                self.dims.n_audio_head,
+                self.dims.n_audio_layer,
+            )
        self.decoder = TextDecoder(
            self.dims.n_vocab,
            self.dims.n_text_ctx,
--- a/whisperlivekit/timed_objects.py
+++ b/whisperlivekit/timed_objects.py
@@ -1,10 +1,16 @@
 from dataclasses import dataclass
 from typing import Optional
+from datetime import timedelta
+
+def format_time(seconds: float) -> str:
+    """Format seconds as HH:MM:SS."""
+    return str(timedelta(seconds=int(seconds)))
+

@dataclass
 class TimedText:
-    start: Optional[float]
-    end: Optional[float]
+    start: Optional[float] = 0
+    end: Optional[float] = 0
    text: Optional[str] = ''
    speaker: Optional[int] = -1
    probability: Optional[float] = None
@@ -31,6 +37,24 @@ class SpeakerSegment(TimedText):
    """
    pass

+@dataclass
+class Translation(TimedText):
+    pass
+
@dataclass
 class Silence():
-    duration: float
+    duration: float
+    
+    
+@dataclass
+class Line(TimedText):
+    translation: str = ''
+    
+    def to_dict(self):
+        return {
+            'speaker': int(self.speaker),
+            'text': self.text,
+            'translation': self.translation,
+            'start': format_time(self.start),
+            'end': format_time(self.end),
+        }
--- a/whisperlivekit/translation/init.py
+++ b/whisperlivekit/translation/init.py
--- a/whisperlivekit/translation/mapping_languages.py
+++ b/whisperlivekit/translation/mapping_languages.py
@@ -0,0 +1,182 @@
+"""
+adapted from https://store.crowdin.com/custom-mt
+"""
+
+LANGUAGES = [
+    {"name": "Afrikaans", "nllb": "afr_Latn", "crowdin": "af"},
+    {"name": "Akan", "nllb": "aka_Latn", "crowdin": "ak"},
+    {"name": "Amharic", "nllb": "amh_Ethi", "crowdin": "am"},
+    {"name": "Assamese", "nllb": "asm_Beng", "crowdin": "as"},
+    {"name": "Asturian", "nllb": "ast_Latn", "crowdin": "ast"},
+    {"name": "Bashkir", "nllb": "bak_Cyrl", "crowdin": "ba"},
+    {"name": "Bambara", "nllb": "bam_Latn", "crowdin": "bm"},
+    {"name": "Balinese", "nllb": "ban_Latn", "crowdin": "ban"},
+    {"name": "Belarusian", "nllb": "bel_Cyrl", "crowdin": "be"},
+    {"name": "Bengali", "nllb": "ben_Beng", "crowdin": "bn"},
+    {"name": "Bosnian", "nllb": "bos_Latn", "crowdin": "bs"},
+    {"name": "Bulgarian", "nllb": "bul_Cyrl", "crowdin": "bg"},
+    {"name": "Catalan", "nllb": "cat_Latn", "crowdin": "ca"},
+    {"name": "Cebuano", "nllb": "ceb_Latn", "crowdin": "ceb"},
+    {"name": "Czech", "nllb": "ces_Latn", "crowdin": "cs"},
+    {"name": "Welsh", "nllb": "cym_Latn", "crowdin": "cy"},
+    {"name": "Danish", "nllb": "dan_Latn", "crowdin": "da"},
+    {"name": "German", "nllb": "deu_Latn", "crowdin": "de"},
+    {"name": "Dzongkha", "nllb": "dzo_Tibt", "crowdin": "dz"},
+    {"name": "Greek", "nllb": "ell_Grek", "crowdin": "el"},
+    {"name": "English", "nllb": "eng_Latn", "crowdin": "en"},
+    {"name": "Esperanto", "nllb": "epo_Latn", "crowdin": "eo"},
+    {"name": "Estonian", "nllb": "est_Latn", "crowdin": "et"},
+    {"name": "Basque", "nllb": "eus_Latn", "crowdin": "eu"},
+    {"name": "Ewe", "nllb": "ewe_Latn", "crowdin": "ee"},
+    {"name": "Faroese", "nllb": "fao_Latn", "crowdin": "fo"},
+    {"name": "Fijian", "nllb": "fij_Latn", "crowdin": "fj"},
+    {"name": "Finnish", "nllb": "fin_Latn", "crowdin": "fi"},
+    {"name": "French", "nllb": "fra_Latn", "crowdin": "fr"},
+    {"name": "Friulian", "nllb": "fur_Latn", "crowdin": "fur-IT"},
+    {"name": "Scottish Gaelic", "nllb": "gla_Latn", "crowdin": "gd"},
+    {"name": "Irish", "nllb": "gle_Latn", "crowdin": "ga-IE"},
+    {"name": "Galician", "nllb": "glg_Latn", "crowdin": "gl"},
+    {"name": "Guarani", "nllb": "grn_Latn", "crowdin": "gn"},
+    {"name": "Gujarati", "nllb": "guj_Gujr", "crowdin": "gu-IN"},
+    {"name": "Haitian Creole", "nllb": "hat_Latn", "crowdin": "ht"},
+    {"name": "Hausa", "nllb": "hau_Latn", "crowdin": "ha"},
+    {"name": "Hebrew", "nllb": "heb_Hebr", "crowdin": "he"},
+    {"name": "Hindi", "nllb": "hin_Deva", "crowdin": "hi"},
+    {"name": "Croatian", "nllb": "hrv_Latn", "crowdin": "hr"},
+    {"name": "Hungarian", "nllb": "hun_Latn", "crowdin": "hu"},
+    {"name": "Armenian", "nllb": "hye_Armn", "crowdin": "hy-AM"},
+    {"name": "Igbo", "nllb": "ibo_Latn", "crowdin": "ig"},
+    {"name": "Indonesian", "nllb": "ind_Latn", "crowdin": "id"},
+    {"name": "Icelandic", "nllb": "isl_Latn", "crowdin": "is"},
+    {"name": "Italian", "nllb": "ita_Latn", "crowdin": "it"},
+    {"name": "Javanese", "nllb": "jav_Latn", "crowdin": "jv"},
+    {"name": "Japanese", "nllb": "jpn_Jpan", "crowdin": "ja"},
+    {"name": "Kabyle", "nllb": "kab_Latn", "crowdin": "kab"},
+    {"name": "Kannada", "nllb": "kan_Knda", "crowdin": "kn"},
+    {"name": "Georgian", "nllb": "kat_Geor", "crowdin": "ka"},
+    {"name": "Kazakh", "nllb": "kaz_Cyrl", "crowdin": "kk"},
+    {"name": "Khmer", "nllb": "khm_Khmr", "crowdin": "km"},
+    {"name": "Kinyarwanda", "nllb": "kin_Latn", "crowdin": "rw"},
+    {"name": "Kyrgyz", "nllb": "kir_Cyrl", "crowdin": "ky"},
+    {"name": "Korean", "nllb": "kor_Hang", "crowdin": "ko"},
+    {"name": "Lao", "nllb": "lao_Laoo", "crowdin": "lo"},
+    {"name": "Ligurian", "nllb": "lij_Latn", "crowdin": "lij"},
+    {"name": "Limburgish", "nllb": "lim_Latn", "crowdin": "li"},
+    {"name": "Lingala", "nllb": "lin_Latn", "crowdin": "ln"},
+    {"name": "Lithuanian", "nllb": "lit_Latn", "crowdin": "lt"},
+    {"name": "Luxembourgish", "nllb": "ltz_Latn", "crowdin": "lb"},
+    {"name": "Maithili", "nllb": "mai_Deva", "crowdin": "mai"},
+    {"name": "Malayalam", "nllb": "mal_Mlym", "crowdin": "ml-IN"},
+    {"name": "Marathi", "nllb": "mar_Deva", "crowdin": "mr"},
+    {"name": "Macedonian", "nllb": "mkd_Cyrl", "crowdin": "mk"},
+    {"name": "Maltese", "nllb": "mlt_Latn", "crowdin": "mt"},
+    {"name": "Mossi", "nllb": "mos_Latn", "crowdin": "mos"},
+    {"name": "Maori", "nllb": "mri_Latn", "crowdin": "mi"},
+    {"name": "Burmese", "nllb": "mya_Mymr", "crowdin": "my"},
+    {"name": "Dutch", "nllb": "nld_Latn", "crowdin": "nl"},
+    {"name": "Norwegian Nynorsk", "nllb": "nno_Latn", "crowdin": "nn-NO"},
+    {"name": "Nepali", "nllb": "npi_Deva", "crowdin": "ne-NP"},
+    {"name": "Northern Sotho", "nllb": "nso_Latn", "crowdin": "nso"},
+    {"name": "Occitan", "nllb": "oci_Latn", "crowdin": "oc"},
+    {"name": "Odia", "nllb": "ory_Orya", "crowdin": "or"},
+    {"name": "Papiamento", "nllb": "pap_Latn", "crowdin": "pap"},
+    {"name": "Polish", "nllb": "pol_Latn", "crowdin": "pl"},
+    {"name": "Portuguese", "nllb": "por_Latn", "crowdin": "pt-PT"},
+    {"name": "Dari", "nllb": "prs_Arab", "crowdin": "fa-AF"},
+    {"name": "Romanian", "nllb": "ron_Latn", "crowdin": "ro"},
+    {"name": "Rundi", "nllb": "run_Latn", "crowdin": "rn"},
+    {"name": "Russian", "nllb": "rus_Cyrl", "crowdin": "ru"},
+    {"name": "Sango", "nllb": "sag_Latn", "crowdin": "sg"},
+    {"name": "Sanskrit", "nllb": "san_Deva", "crowdin": "sa"},
+    {"name": "Santali", "nllb": "sat_Olck", "crowdin": "sat"},
+    {"name": "Sinhala", "nllb": "sin_Sinh", "crowdin": "si-LK"},
+    {"name": "Slovak", "nllb": "slk_Latn", "crowdin": "sk"},
+    {"name": "Slovenian", "nllb": "slv_Latn", "crowdin": "sl"},
+    {"name": "Shona", "nllb": "sna_Latn", "crowdin": "sn"},
+    {"name": "Sindhi", "nllb": "snd_Arab", "crowdin": "sd"},
+    {"name": "Somali", "nllb": "som_Latn", "crowdin": "so"},
+    {"name": "Southern Sotho", "nllb": "sot_Latn", "crowdin": "st"},
+    {"name": "Spanish", "nllb": "spa_Latn", "crowdin": "es-ES"},
+    {"name": "Sardinian", "nllb": "srd_Latn", "crowdin": "sc"},
+    {"name": "Swati", "nllb": "ssw_Latn", "crowdin": "ss"},
+    {"name": "Sundanese", "nllb": "sun_Latn", "crowdin": "su"},
+    {"name": "Swedish", "nllb": "swe_Latn", "crowdin": "sv-SE"},
+    {"name": "Swahili", "nllb": "swh_Latn", "crowdin": "sw"},
+    {"name": "Tamil", "nllb": "tam_Taml", "crowdin": "ta"},
+    {"name": "Tatar", "nllb": "tat_Cyrl", "crowdin": "tt-RU"},
+    {"name": "Telugu", "nllb": "tel_Telu", "crowdin": "te"},
+    {"name": "Tajik", "nllb": "tgk_Cyrl", "crowdin": "tg"},
+    {"name": "Tagalog", "nllb": "tgl_Latn", "crowdin": "tl"},
+    {"name": "Thai", "nllb": "tha_Thai", "crowdin": "th"},
+    {"name": "Tigrinya", "nllb": "tir_Ethi", "crowdin": "ti"},
+    {"name": "Tswana", "nllb": "tsn_Latn", "crowdin": "tn"},
+    {"name": "Tsonga", "nllb": "tso_Latn", "crowdin": "ts"},
+    {"name": "Turkmen", "nllb": "tuk_Latn", "crowdin": "tk"},
+    {"name": "Turkish", "nllb": "tur_Latn", "crowdin": "tr"},
+    {"name": "Uyghur", "nllb": "uig_Arab", "crowdin": "ug"},
+    {"name": "Ukrainian", "nllb": "ukr_Cyrl", "crowdin": "uk"},
+    {"name": "Venetian", "nllb": "vec_Latn", "crowdin": "vec"},
+    {"name": "Vietnamese", "nllb": "vie_Latn", "crowdin": "vi"},
+    {"name": "Wolof", "nllb": "wol_Latn", "crowdin": "wo"},
+    {"name": "Xhosa", "nllb": "xho_Latn", "crowdin": "xh"},
+    {"name": "Yoruba", "nllb": "yor_Latn", "crowdin": "yo"},
+    {"name": "Zulu", "nllb": "zul_Latn", "crowdin": "zu"},
+]
+
+NAME_TO_NLLB = {lang["name"]: lang["nllb"] for lang in LANGUAGES}
+NAME_TO_CROWDIN = {lang["name"]: lang["crowdin"] for lang in LANGUAGES}
+CROWDIN_TO_NLLB = {lang["crowdin"]: lang["nllb"] for lang in LANGUAGES}
+NLLB_TO_CROWDIN = {lang["nllb"]: lang["crowdin"] for lang in LANGUAGES}
+CROWDIN_TO_NAME = {lang["crowdin"]: lang["name"] for lang in LANGUAGES}
+NLLB_TO_NAME = {lang["nllb"]: lang["name"] for lang in LANGUAGES}
+
+
+def get_nllb_code(crowdin_code):
+    return CROWDIN_TO_NLLB.get(crowdin_code, None)
+
+
+def get_crowdin_code(nllb_code):
+    return NLLB_TO_CROWDIN.get(nllb_code)
+
+
+def get_language_name_by_crowdin(crowdin_code):
+    return CROWDIN_TO_NAME.get(crowdin_code)
+
+
+def get_language_name_by_nllb(nllb_code):
+    return NLLB_TO_NAME.get(nllb_code)
+
+
+def get_language_info(identifier, identifier_type="auto"):
+    if identifier_type == "auto":
+        for lang in LANGUAGES:
+            if (lang["name"].lower() == identifier.lower() or 
+                lang["nllb"] == identifier or 
+                lang["crowdin"] == identifier):
+                return lang
+    elif identifier_type == "name":
+        for lang in LANGUAGES:
+            if lang["name"].lower() == identifier.lower():
+                return lang
+    elif identifier_type == "nllb":
+        for lang in LANGUAGES:
+            if lang["nllb"] == identifier:
+                return lang
+    elif identifier_type == "crowdin":
+        for lang in LANGUAGES:
+            if lang["crowdin"] == identifier:
+                return lang
+    
+    return None
+
+
+def list_all_languages():
+    return [lang["name"] for lang in LANGUAGES]
+
+
+def list_all_nllb_codes():
+    return [lang["nllb"] for lang in LANGUAGES]
+
+
+def list_all_crowdin_codes():
+    return [lang["crowdin"] for lang in LANGUAGES]
--- a/whisperlivekit/translation/translation.py
+++ b/whisperlivekit/translation/translation.py
@@ -0,0 +1,137 @@
+import ctranslate2
+import torch
+import transformers
+from dataclasses import dataclass
+import huggingface_hub
+from whisperlivekit.translation.mapping_languages import get_nllb_code
+from whisperlivekit.timed_objects import Translation
+
+
+#In diarization case, we may want to translate just one speaker, or at least start the sentences there
+
+PUNCTUATION_MARKS = {'.', '!', '?', '。', '！', '？'}
+
+
+@dataclass
+class TranslationModel():
+    translator: ctranslate2.Translator
+    tokenizer: dict
+
+def load_model(src_langs):
+    MODEL = 'nllb-200-distilled-600M-ctranslate2'
+    MODEL_GUY = 'entai2965'
+    huggingface_hub.snapshot_download(MODEL_GUY + '/' + MODEL,local_dir=MODEL)
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    translator = ctranslate2.Translator(MODEL,device=device)
+    tokenizer = dict()
+    for src_lang in src_langs:
+        tokenizer[src_lang] = transformers.AutoTokenizer.from_pretrained(MODEL, src_lang=src_lang, clean_up_tokenization_spaces=True)
+    return TranslationModel(
+        translator=translator,
+        tokenizer=tokenizer
+    )
+
+def translate(input, translation_model, tgt_lang):
+    source = translation_model.tokenizer.convert_ids_to_tokens(translation_model.tokenizer.encode(input))
+    target_prefix = [tgt_lang]
+    results = translation_model.translator.translate_batch([source], target_prefix=[target_prefix])
+    target = results[0].hypotheses[0][1:]
+    return translation_model.tokenizer.decode(translation_model.tokenizer.convert_tokens_to_ids(target))
+
+class OnlineTranslation:
+    def __init__(self, translation_model: TranslationModel, input_languages: list, output_languages: list):
+        self.buffer = []
+        self.len_processed_buffer = 0
+        self.translation_remaining = Translation()
+        self.validated = []
+        self.translation_pending_validation = ''
+        self.translation_model = translation_model
+        self.input_languages = input_languages
+        self.output_languages = output_languages
+
+    def compute_common_prefix(self, results):
+        #we dont want want to prune the result for the moment. 
+        if not self.buffer:
+            self.buffer = results
+        else:
+            for i in range(min(len(self.buffer), len(results))):
+                if self.buffer[i] != results[i]:
+                    self.commited.extend(self.buffer[:i])
+                    self.buffer = results[i:]
+
+    def translate(self, input, input_lang=None, output_lang=None):
+        if not input:
+            return ""
+        if input_lang is None:
+            input_lang = self.input_languages[0]
+        if output_lang is None:
+            output_lang = self.output_languages[0]
+        nllb_output_lang = get_nllb_code(output_lang)
+            
+        source = self.translation_model.tokenizer[input_lang].convert_ids_to_tokens(self.translation_model.tokenizer[input_lang].encode(input))   
+        results = self.translation_model.translator.translate_batch([source], target_prefix=[[nllb_output_lang]]) #we can use return_attention=True to try to optimize the stuff.
+        target = results[0].hypotheses[0][1:]
+        results = self.translation_model.tokenizer[input_lang].decode(self.translation_model.tokenizer[input_lang].convert_tokens_to_ids(target))
+        return results
+
+    def translate_tokens(self, tokens):
+        if tokens:
+            text = ' '.join([token.text for token in tokens])
+            start = tokens[0].start
+            end = tokens[-1].end
+            translated_text = self.translate(text)
+            translation = Translation(
+                text=translated_text,
+                start=start,
+                end=end,
+            )
+            return translation
+        return None
+            
+        
+
+    def insert_tokens(self, tokens):
+        self.buffer.extend(tokens)
+        pass
+    
+    def process(self):
+        i = 0
+        if len(self.buffer) < self.len_processed_buffer + 3: #nothing new to process
+            return self.validated + [self.translation_remaining]
+        while i < len(self.buffer):
+            if self.buffer[i].text in PUNCTUATION_MARKS:
+                translation_sentence = self.translate_tokens(self.buffer[:i+1])
+                self.validated.append(translation_sentence)
+                self.buffer = self.buffer[i+1:]
+                i = 0
+            else:
+                i+=1
+        self.translation_remaining = self.translate_tokens(self.buffer)
+        self.len_processed_buffer = len(self.buffer)
+        return self.validated + [self.translation_remaining]
+                
+
+if __name__ == '__main__':
+    output_lang = 'fr'
+    input_lang = "en"
+    
+    
+    test_string = """
+    Transcription technology has improved so much in the past few years. Have you noticed how accurate real-time speech-to-text is now?
+    """
+    test = test_string.split(' ')
+    step = len(test) // 3
+    
+    shared_model = load_model([input_lang])
+    online_translation = OnlineTranslation(shared_model, input_languages=[input_lang], output_languages=[output_lang])
+        
+    for id in range(5):
+        val = test[id*step : (id+1)*step]
+        val_str = ' '.join(val)
+        result = online_translation.translate(val_str)
+        print(result)
+    
+    
+    
+    
+    # print(result)
--- a/whisperlivekit/warmup.py
+++ b/whisperlivekit/warmup.py
@@ -31,21 +31,21 @@ def load_file(warmup_file=None, timeout=5):
                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
+                return None
            finally:
                socket.setdefaulttimeout(original_timeout)
    elif not warmup_file:
-        return False 
+        return None 
    
    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
+        return None
    
    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 None
    return audio

 def warmup_asr(asr, warmup_file=None, timeout=5):
--- a/whisperlivekit/web/live_transcription.css
+++ b/whisperlivekit/web/live_transcription.css
@@ -74,10 +74,13 @@

 body {
  font-family: ui-sans-serif, system-ui, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
-  margin: 20px;
+  margin: 0;
  text-align: center;
  background-color: var(--bg);
  color: var(--text);
+  height: 100vh;
+  display: flex;
+  flex-direction: column;
 }

 /* Record button */
@@ -168,9 +171,18 @@ body {
 }

 #status {
-  margin-top: 20px;
+  margin-top: 15px;
  font-size: 16px;
  color: var(--text);
+  margin-bottom: 0;
+}
+
+.header-container {
+  position: sticky;
+  top: 0;
+  background-color: var(--bg);
+  z-index: 100;
+  padding: 20px;
 }

 /* Settings */
@@ -179,12 +191,11 @@ body {
  justify-content: center;
  align-items: center;
  gap: 15px;
-  margin-top: 20px;
 }

 .settings {
  display: flex;
-  flex-direction: column;
+  flex-wrap: wrap;
  align-items: flex-start;
  gap: 12px;
 }
@@ -198,23 +209,27 @@ body {

 #chunkSelector,
 #websocketInput,
-#themeSelector {
+#themeSelector,
+#microphoneSelect {
  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;
+  max-height: 30px;
 }

-#websocketInput {
-  width: 220px;
+#microphoneSelect {
+  width: 100%;
+  max-width: 190px;
+  min-width: 120px;
 }

 #chunkSelector:focus,
 #websocketInput:focus,
-#themeSelector:focus {
+#themeSelector:focus,
+#microphoneSelect:focus {
  outline: none;
  border-color: #007bff;
  box-shadow: 0 0 0 3px rgba(0, 123, 255, 0.15);
@@ -247,9 +262,9 @@ label {
 }

 .theme-selector-container {
-  position: absolute;
-  top: 20px;
-  right: 20px;
+  display: flex;
+  align-items: center;
+  margin-top: 17px;
 }

 .segmented label {
@@ -293,9 +308,21 @@ label {
  border-radius: 999px;
 }

+.transcript-container {
+  flex: 1;
+  overflow-y: auto;
+  padding: 20px;
+  scrollbar-width: none;
+  -ms-overflow-style: none;
+}
+
+.transcript-container::-webkit-scrollbar {
+  display: none;
+}
+
 /* Transcript area */
 #linesTranscript {
-  margin: 20px auto;
+  margin: 0 auto;
  max-width: 700px;
  text-align: left;
  font-size: 16px;
@@ -341,6 +368,27 @@ label {
  color: var(--label-trans-text);
 }

+.label_translation {
+  background-color: var(--chip-bg);
+  border-radius: 10px;
+  padding: 4px 8px;
+  margin-top: 4px;
+  font-size: 14px;
+  color: var(--text);
+  display: flex;
+  align-items: flex-start;
+  gap: 4px;
+}
+
+.label_translation img {
+  margin-top: 2px;
+}
+
+.label_translation img {
+  width: 12px;
+  height: 12px;
+}
+
 #timeInfo {
  color: var(--muted);
  margin-left: 10px;
@@ -390,6 +438,7 @@ label {
  font-size: 13px;
  border-radius: 30px;
  padding: 2px 10px;
+  display: none;
 }

 .loading {
@@ -400,3 +449,69 @@ label {
  font-size: 14px;
  margin-bottom: 0px;
 }
+
+/* for smaller screens */
+@media (max-width: 768px) {
+  .header-container {
+    padding: 15px;
+  }
+  
+  .settings-container {
+    flex-direction: column;
+    gap: 10px;
+  }
+  
+  .settings {
+    justify-content: center;
+    gap: 8px;
+  }
+  
+  .field {
+    align-items: center;
+  }
+  
+  #websocketInput,
+  #microphoneSelect {
+    min-width: 100px;
+    max-width: 160px;
+  }
+  
+  .theme-selector-container {
+    margin-top: 10px;
+  }
+  
+  .transcript-container {
+    padding: 15px;
+  }
+}
+
+@media (max-width: 480px) {
+  .header-container {
+    padding: 10px;
+  }
+  
+  .settings {
+    flex-direction: column;
+    align-items: center;
+    gap: 6px;
+  }
+  
+  #websocketInput,
+  #microphoneSelect {
+    max-width: 140px;
+  }
+  
+  .segmented label {
+    padding: 4px 8px;
+    font-size: 12px;
+  }
+  
+  .segmented img {
+    width: 14px;
+    height: 14px;
+  }
+  
+  .transcript-container {
+    padding: 10px;
+  }
+}
--- a/whisperlivekit/web/live_transcription.html
+++ b/whisperlivekit/web/live_transcription.html
@@ -1,61 +1,73 @@
 <!DOCTYPE html>
 <html lang="en">
+
 <head>
-  <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" />
+    <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 class="header-container">
+        <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 class="field">
+                    <label id="microphoneSelectLabel" for="microphoneSelect">Select Microphone</label>
+                    <select id="microphoneSelect">
+                        <option value="">Default Microphone</option>
+                    </select>
+                </div>
+
+                <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>
+
+                        <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>
+
+                        <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>
+            </div>
        </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>
+        
+        <p id="status"></p>
    </div>
-  </div>

-  <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>
-
-      <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>
-
-      <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 class="transcript-container">
+        <div id="linesTranscript"></div>
    </div>
-  </div>

-  <p id="status"></p>
-
-  <div id="linesTranscript"></div>
-
-  <script src="/web/live_transcription.js"></script>
+    <script src="/web/live_transcription.js"></script>
 </body>
-</html>
+
+</html>
--- a/whisperlivekit/web/live_transcription.js
+++ b/whisperlivekit/web/live_transcription.js
@@ -18,6 +18,8 @@ let animationFrame = null;
 let waitingForStop = false;
 let lastReceivedData = null;
 let lastSignature = null;
+let availableMicrophones = [];
+let selectedMicrophoneId = null;

 waveCanvas.width = 60 * (window.devicePixelRatio || 1);
 waveCanvas.height = 30 * (window.devicePixelRatio || 1);
@@ -31,6 +33,7 @@ const websocketDefaultSpan = document.getElementById("wsDefaultUrl");
 const linesTranscriptDiv = document.getElementById("linesTranscript");
 const timerElement = document.querySelector(".timer");
 const themeRadios = document.querySelectorAll('input[name="theme"]');
+const microphoneSelect = document.getElementById("microphoneSelect");

 function getWaveStroke() {
  const styles = getComputedStyle(document.documentElement);
@@ -82,6 +85,61 @@ if (darkMq && darkMq.addEventListener) {
  darkMq.addListener(handleOsThemeChange);
 }

+async function enumerateMicrophones() {
+  try {
+    const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+    stream.getTracks().forEach(track => track.stop());
+
+    const devices = await navigator.mediaDevices.enumerateDevices();
+    availableMicrophones = devices.filter(device => device.kind === 'audioinput');
+
+    populateMicrophoneSelect();
+    console.log(`Found ${availableMicrophones.length} microphone(s)`);
+  } catch (error) {
+    console.error('Error enumerating microphones:', error);
+    statusText.textContent = "Error accessing microphones. Please grant permission.";
+  }
+}
+
+function populateMicrophoneSelect() {
+  if (!microphoneSelect) return;
+
+  microphoneSelect.innerHTML = '<option value="">Default Microphone</option>';
+
+  availableMicrophones.forEach((device, index) => {
+    const option = document.createElement('option');
+    option.value = device.deviceId;
+    option.textContent = device.label || `Microphone ${index + 1}`;
+    microphoneSelect.appendChild(option);
+  });
+
+  const savedMicId = localStorage.getItem('selectedMicrophone');
+  if (savedMicId && availableMicrophones.some(mic => mic.deviceId === savedMicId)) {
+    microphoneSelect.value = savedMicId;
+    selectedMicrophoneId = savedMicId;
+  }
+}
+
+function handleMicrophoneChange() {
+  selectedMicrophoneId = microphoneSelect.value || null;
+  localStorage.setItem('selectedMicrophone', selectedMicrophoneId || '');
+
+  const selectedDevice = availableMicrophones.find(mic => mic.deviceId === selectedMicrophoneId);
+  const deviceName = selectedDevice ? selectedDevice.label : 'Default Microphone';
+
+  console.log(`Selected microphone: ${deviceName}`);
+  statusText.textContent = `Microphone changed to: ${deviceName}`;
+
+  if (isRecording) {
+    statusText.textContent = "Switching microphone... Please wait.";
+    stopRecording().then(() => {
+      setTimeout(() => {
+        toggleRecording();
+      }, 1000);
+    });
+  }
+}
+
 // Helpers
 function fmt1(x) {
  const n = Number(x);
@@ -235,7 +293,7 @@ function renderLinesWithBuffer(
  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 })),
+    lines: (lines || []).map((it) => ({ speaker: it.speaker, text: it.text, start: it.start, end: it.end })),
    buffer_transcription: buffer_transcription || "",
    buffer_diarization: buffer_diarization || "",
    status: current_status,
@@ -258,8 +316,8 @@ function renderLinesWithBuffer(
  const linesHtml = (lines || [])
    .map((item, idx) => {
      let timeInfo = "";
-      if (item.beg !== undefined && item.end !== undefined) {
-        timeInfo = ` ${item.beg} - ${item.end}`;
+      if (item.start !== undefined && item.end !== undefined) {
+        timeInfo = ` ${item.start} - ${item.end}`;
      }

      let speakerLabel = "";
@@ -274,6 +332,13 @@ function renderLinesWithBuffer(
      }

      let currentLineText = item.text || "";
+      
+      if (item.translation) {
+        currentLineText += `<div class="label_translation">
+          <img src="/web/src/translate.svg" alt="Translation" width="12" height="12" />
+          <span>${item.translation}</span>
+        </div>`;
+      }

      if (idx === lines.length - 1) {
        if (!isFinalizing && item.speaker !== -2) {
@@ -315,7 +380,10 @@ function renderLinesWithBuffer(
    .join("");

  linesTranscriptDiv.innerHTML = linesHtml;
-  window.scrollTo({ top: document.body.scrollHeight, behavior: "smooth" });
+  const transcriptContainer = document.querySelector('.transcript-container');
+  if (transcriptContainer) {
+    transcriptContainer.scrollTo({ top: transcriptContainer.scrollHeight, behavior: "smooth" });
+  }
 }

 function updateTimer() {
@@ -377,7 +445,11 @@ async function startRecording() {
      console.log("Error acquiring wake lock.");
    }

-    const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+    const audioConstraints = selectedMicrophoneId 
+      ? { audio: { deviceId: { exact: selectedMicrophoneId } } }
+      : { audio: true };
+
+    const stream = await navigator.mediaDevices.getUserMedia(audioConstraints);

    audioContext = new (window.AudioContext || window.webkitAudioContext)();
    analyser = audioContext.createAnalyser();
@@ -516,3 +588,22 @@ function updateUI() {
 }

 recordButton.addEventListener("click", toggleRecording);
+
+if (microphoneSelect) {
+  microphoneSelect.addEventListener("change", handleMicrophoneChange);
+}
+document.addEventListener('DOMContentLoaded', async () => {
+  try {
+    await enumerateMicrophones();
+  } catch (error) {
+    console.log("Could not enumerate microphones on load:", error);
+  }
+});
+navigator.mediaDevices.addEventListener('devicechange', async () => {
+  console.log('Device change detected, re-enumerating microphones');
+  try {
+    await enumerateMicrophones();
+  } catch (error) {
+    console.log("Error re-enumerating microphones:", error);
+  }
+});
--- a/whisperlivekit/web/src/settings.svg
+++ b/whisperlivekit/web/src/settings.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="M433-80q-27 0-46.5-18T363-142l-9-66q-13-5-24.5-12T307-235l-62 26q-25 11-50 2t-39-32l-47-82q-14-23-8-49t27-43l53-40q-1-7-1-13.5v-27q0-6.5 1-13.5l-53-40q-21-17-27-43t8-49l47-82q14-23 39-32t50 2l62 26q11-8 23-15t24-12l9-66q4-26 23.5-44t46.5-18h94q27 0 46.5 18t23.5 44l9 66q13 5 24.5 12t22.5 15l62-26q25-11 50-2t39 32l47 82q14 23 8 49t-27 43l-53 40q1 7 1 13.5v27q0 6.5-2 13.5l53 40q21 17 27 43t-8 49l-48 82q-14 23-39 32t-50-2l-60-26q-11 8-23 15t-24 12l-9 66q-4 26-23.5 44T527-80h-94Zm7-80h79l14-106q31-8 57.5-23.5T639-327l99 41 39-68-86-65q5-14 7-29.5t2-31.5q0-16-2-31.5t-7-29.5l86-65-39-68-99 42q-22-23-48.5-38.5T533-694l-13-106h-79l-14 106q-31 8-57.5 23.5T321-633l-99-41-39 68 86 64q-5 15-7 30t-2 32q0 16 2 31t7 30l-86 65 39 68 99-42q22 23 48.5 38.5T427-266l13 106Zm42-180q58 0 99-41t41-99q0-58-41-99t-99-41q-59 0-99.5 41T342-480q0 58 40.5 99t99.5 41Zm-2-140Z"/></svg>
--- a/whisperlivekit/web/src/translate.svg
+++ b/whisperlivekit/web/src/translate.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="m603-202-34 97q-4 11-14 18t-22 7q-20 0-32.5-16.5T496-133l152-402q5-11 15-18t22-7h30q12 0 22 7t15 18l152 403q8 19-4 35.5T868-80q-13 0-22.5-7T831-106l-34-96H603ZM362-401 188-228q-11 11-27.5 11.5T132-228q-11-11-11-28t11-28l174-174q-35-35-63.5-80T190-640h84q20 39 40 68t48 58q33-33 68.5-92.5T484-720H80q-17 0-28.5-11.5T40-760q0-17 11.5-28.5T80-800h240v-40q0-17 11.5-28.5T360-880q17 0 28.5 11.5T400-840v40h240q17 0 28.5 11.5T680-760q0 17-11.5 28.5T640-720h-76q-21 72-63 148t-83 116l96 98-30 82-122-125Zm266 129h144l-72-204-72 204Z"/></svg>
--- a/whisperlivekit/web/web_interface.py
+++ b/whisperlivekit/web/web_interface.py
@@ -1,5 +1,6 @@
 import logging
 import importlib.resources as resources
+import base64

 logger = logging.getLogger(__name__)

@@ -12,6 +13,60 @@ def get_web_interface_html():
        logger.error(f"Error loading web interface HTML: {e}")
        return "<html><body><h1>Error loading interface</h1></body></html>"

+def get_inline_ui_html():
+    """Returns the complete web interface HTML with all assets embedded in a single call."""
+    try:
+        with resources.files('whisperlivekit.web').joinpath('live_transcription.html').open('r', encoding='utf-8') as f:
+            html_content = f.read()        
+        with resources.files('whisperlivekit.web').joinpath('live_transcription.css').open('r', encoding='utf-8') as f:
+            css_content = f.read()
+        with resources.files('whisperlivekit.web').joinpath('live_transcription.js').open('r', encoding='utf-8') as f:
+            js_content = f.read()
+        
+        # SVG files
+        with resources.files('whisperlivekit.web').joinpath('src', 'system_mode.svg').open('r', encoding='utf-8') as f:
+            system_svg = f.read()
+            system_data_uri = f"data:image/svg+xml;base64,{base64.b64encode(system_svg.encode('utf-8')).decode('utf-8')}"
+        with resources.files('whisperlivekit.web').joinpath('src', 'light_mode.svg').open('r', encoding='utf-8') as f:
+            light_svg = f.read()
+            light_data_uri = f"data:image/svg+xml;base64,{base64.b64encode(light_svg.encode('utf-8')).decode('utf-8')}"
+        with resources.files('whisperlivekit.web').joinpath('src', 'dark_mode.svg').open('r', encoding='utf-8') as f:
+            dark_svg = f.read()
+            dark_data_uri = f"data:image/svg+xml;base64,{base64.b64encode(dark_svg.encode('utf-8')).decode('utf-8')}"
+        
+        # Replace external references
+        html_content = html_content.replace(
+            '<link rel="stylesheet" href="/web/live_transcription.css" />',
+            f'<style>\n{css_content}\n</style>'
+        )
+        
+        html_content = html_content.replace(
+            '<script src="/web/live_transcription.js"></script>',
+            f'<script>\n{js_content}\n</script>'
+        )
+        
+        # Replace SVG references
+        html_content = html_content.replace(
+            '<img src="/web/src/system_mode.svg" alt="" />',
+            f'<img src="{system_data_uri}" alt="" />'
+        )
+        
+        html_content = html_content.replace(
+            '<img src="/web/src/light_mode.svg" alt="" />',
+            f'<img src="{light_data_uri}" alt="" />'
+        )
+        
+        html_content = html_content.replace(
+            '<img src="/web/src/dark_mode.svg" alt="" />',
+            f'<img src="{dark_data_uri}" alt="" />'
+        )
+        
+        return html_content
+        
+    except Exception as e:
+        logger.error(f"Error creating embedded web interface: {e}")
+        return "<html><body><h1>Error loading embedded interface</h1></body></html>"
+

 if __name__ == '__main__':
    
@@ -28,6 +83,6 @@ if __name__ == '__main__':
    
    @app.get("/")
    async def get():
-        return HTMLResponse(get_web_interface_html())
+        return HTMLResponse(get_inline_ui_html())

-    uvicorn.run(app=app)
+    uvicorn.run(app=app)
Author	SHA1	Message	Date
Quentin Fuxa	babe93b99a	to 0.2.9	2025-09-11 21:36:32 +02:00
Quentin Fuxa	a4e9f3cab7	support for raw PCM input option by @YeonjunNotFR	2025-09-11 21:32:11 +02:00
Quentin Fuxa	b06866877a	add --disable-punctuation-split option	2025-09-11 21:03:00 +02:00
Quentin Fuxa	967cdfebc8	fix Translation imports	2025-09-11 21:03:00 +02:00
Quentin Fuxa	3c11c60126	fix by @treeaaa	2025-09-11 21:03:00 +02:00
Quentin Fuxa	2963e8a757	translate when at least 3 new tokens	2025-09-09 21:45:00 +02:00
Quentin Fuxa	cb2d4ea88a	audio processor lines use now Lines objects instead of dict	2025-09-09 21:45:00 +02:00
Quentin Fuxa	add7ea07ee	translator takes all the tokens from the queue	2025-09-09 19:55:39 +02:00
Quentin Fuxa	da8726b2cb	Merge pull request #211 from Alexander-ARTV/main Fix type error when setting encoder_feature in simul_whisper->infer for faster whisper encoder	2025-09-09 15:46:59 +02:00
Quentin Fuxa	3358877054	Fix StorageView conversion for CPU/GPU compatibility	2025-09-09 15:44:16 +02:00
Quentin Fuxa	1f7798c7c1	condition on encoder_feature_ctranslate type	2025-09-09 12:16:52 +02:00
Alexander Lindberg	c7b3bb5e58	Fix regression with faster-whisper encoder_feature	2025-09-09 11:18:55 +03:00
Quentin Fuxa	f661f21675	translation asyncio task	2025-09-08 18:34:31 +02:00
Quentin Fuxa	b6164aa59b	translation device determined with torch.device	2025-09-08 11:34:40 +02:00
Quentin Fuxa	4209d7f7c0	Place all tensors on the same device in sortformer diarization	2025-09-08 10:20:57 +02:00
Quentin Fuxa	334b338ab0	use platform to determine system and recommand mlx whisper	2025-09-07 15:49:11 +02:00
Quentin Fuxa	72f33be6f2	translation: use of get_nllb_code	2025-09-07 15:25:14 +02:00
Quentin Fuxa	84890b8e61	Merge pull request #201 from notV3NOM/main Fix: simulstreaming preload model count argument in cli	2025-09-07 15:18:54 +02:00
Quentin Fuxa	c6668adcf3	Merge pull request #200 from notV3NOM/misc docs: add vram usage for large-v3-turbo	2025-09-07 15:17:42 +02:00
notV3NOM	a178ed5c22	fix simulstreaming preload model count argument in cli	2025-09-06 18:18:09 +05:30
notV3NOM	7601c74c9c	add vram usage for large-v3-turbo	2025-09-06 17:56:39 +05:30
Quentin Fuxa	fad9ee4d21	Merge pull request #198 from notV3NOM/main Fix scrolling UX with sticky header controls	2025-09-05 20:46:36 +02:00
Quentin Fuxa	d1a9913c47	nllb v0	2025-09-05 18:02:42 +02:00
notV3NOM	e4ca2623cb	Fix scrolling UX with sticky header controls	2025-09-05 21:25:13 +05:30
Quentin Fuxa	9c1bf37960	fixes #197	2025-09-05 16:34:13 +02:00
Quentin Fuxa	f46528471b	revamp chromium extension settings	2025-09-05 16:19:48 +02:00
Quentin Fuxa	191680940b	Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web	2025-09-04 23:58:51 +02:00
Quentin Fuxa	ee02afec56	workaround to get the list of microphones in the extension	2025-09-04 23:58:48 +02:00
Quentin Fuxa	a458028de2	Merge pull request #196 from notV3NOM/main Fix: Exponentially growing simulstreaming silence timer	2025-09-04 23:05:59 +02:00
notV3NOM	abd8f2c269	Fix exponentially growing simulstreaming silence timer	2025-09-04 21:49:07 +05:30
Quentin Fuxa	f3ad4e39e4	torch.Tensor to torch.as_tensor	2025-09-04 16:39:11 +02:00
Quentin Fuxa	e0a5cbf0e7	v0.1.0 chrome extension	2025-09-04 16:36:28 +02:00
Quentin Fuxa	953697cd86	torch.Tensor to torch.as_tensor	2025-09-04 15:25:39 +02:00
Quentin Fuxa	3bd2122eb4	0.2.8 : only the decoder of whisper is loaded in memory when a different encoder is used	2025-09-02 21:12:25 +02:00
Quentin Fuxa	50b0527858	update architecture	2025-09-01 21:24:12 +02:00
Quentin Fuxa	b044fcdec2	Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web	2025-09-01 14:55:19 +02:00
Quentin Fuxa	b0508fcf2c	mlx/fasterWhisper encoders are loaded once and shared in simulstreaming	2025-09-01 14:55:11 +02:00
Quentin Fuxa	ce89b0aebc	Merge pull request #177 from komiyamma/translate-readme-to-japanese Translate README.md to Japanese	2025-09-01 13:54:50 +02:00
Quentin Fuxa	d5008ed828	mlx/fasterWhisper encoders are loaded once and shared in simulstreaming	2025-09-01 12:33:19 +02:00
Quentin Fuxa	d467716e26	add microphone picker	2025-08-31 10:12:52 +02:00
Quentin Fuxa	199e21b3ef	faster-whisper as an optional encoder alternative for simulstreaming	2025-08-30 23:50:16 +02:00
Quentin Fuxa	1d926f2e67	mlx-whisper used as simulstreaming encoder: improve speed for macos systems	2025-08-30 22:19:11 +02:00
Quentin Fuxa	4a71a391b8	get_web_interface_html to get_inline_ui_html for embedded web interface HTML	2025-08-30 13:44:06 +02:00
google-labs-jules[bot]	d3ed4e46e2	Translate README.md to Japanese Create a Japanese version of the README.md file named ReadmeJP.md. This makes the project more accessible to Japanese-speaking users.	2025-08-30 04:16:18 +00:00
Quentin Fuxa	057a1026d7	Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web	2025-08-29 22:01:04 +02:00
Quentin Fuxa	1ba171a58d	add embedded web interface HTML (single-file version with inline CSS/JS/SVG) ### Added - `get_inline_ui_html()`: generates a self-contained version of the web interface, with CSS, JS, and SVG assets inlined directly into the HTML. useful for environments where serving static files is inconvenient or when a single-call UI delivery is preferred. (cherry picked from commit `aa44a92a67`)	2025-08-29 22:00:59 +02:00
Quentin Fuxa	1adac67155	explanations about model persistency in containers	2025-08-29 21:27:08 +02:00
Quentin Fuxa	42be1a3773	Merge pull request #173 from CoderRahul9904/chore/docker/pytorch-timeout-retries fix: increase pip timeout & retries for torch wheel install	2025-08-29 21:22:30 +02:00
Rahul Mourya	0a49fafa0d	Update Dockerfile fix(docker): increase pip timeout/retries for PyTorch wheel installs	2025-08-30 00:23:59 +05:30
				`@@ -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>`
				`@@ -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>