fixes #307

Dockerfile

@@ -37,9 +37,10 @@ RUN pip3 install --upgrade pip setuptools wheel && \
 COPY . .
 
 # Install WhisperLiveKit directly, allowing for optional dependencies
+# Example: --build-arg EXTRAS="translation"
 RUN if [ -n "$EXTRAS" ]; then \
       echo "Installing with extras: [$EXTRAS]"; \
-      pip install --no-cache-dir whisperlivekit[$EXTRAS]; \
+      pip install --no-cache-dir "whisperlivekit[$EXTRAS]"; \
     else \
       echo "Installing base package only"; \
       pip install --no-cache-dir whisperlivekit; \

README.md

@@ -147,8 +147,8 @@ async def websocket_endpoint(websocket: WebSocket):
 |-----------|-------------|---------|
 | `--model` | Whisper model size. List and recommandations [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/docs/default_and_custom_models.md) | `small` |
 | `--model-path` | Local .pt file/directory **or** Hugging Face repo ID containing the Whisper model. Overrides `--model`. Recommandations [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/docs/default_and_custom_models.md) | `None` |
-| `--language` | List [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/whisper/tokenizer.py). If you use `auto`, the model attempts to detect the language automatically, but it tends to bias towards English. | `auto` |
-| `--target-language` | If sets, translates using [NLLW](https://github.com/QuentinFuxa/NoLanguageLeftWaiting). [200 languages available](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/docs/supported_languages.md). If you want to translate to english, you can also use `--direct-english-translation`. The STT model will try to directly output the translation. | `None` |
+| `--language` | List [here](docs/supported_languages.md). If you use `auto`, the model attempts to detect the language automatically, but it tends to bias towards English. | `auto` |
+| `--target-language` | If sets, translates using [NLLW](https://github.com/QuentinFuxa/NoLanguageLeftWaiting). [200 languages available](docs/supported_languages.md). If you want to translate to english, you can also use `--direct-english-translation`. The STT model will try to directly output the translation. | `None` |
 | `--diarization` | Enable speaker identification | `False` |
 | `--backend-policy` | Streaming strategy: `1`/`simulstreaming` uses AlignAtt SimulStreaming, `2`/`localagreement` uses the LocalAgreement policy | `simulstreaming` |
 | `--backend` | Whisper implementation selector. `auto` picks MLX on macOS (if installed), otherwise Faster-Whisper, otherwise vanilla Whisper. You can also force `mlx-whisper`, `faster-whisper`, `whisper`, or `openai-api` (LocalAgreement only) | `auto` |
@@ -267,7 +267,7 @@ docker run --gpus all -p 8000:8000 --name wlk wlk --model large-v3 --language fr
 #### Customization
 
 - `--build-arg` Options:
-  - `EXTRAS="whisper-timestamped"` - Add extras to the image's installation (no spaces). Remember to set necessary container options!
+  - `EXTRAS="translation"` - Add extras to the image's installation (no spaces). Remember to set necessary container options!
   - `HF_PRECACHE_DIR="./.cache/"` - Pre-load a model cache for faster first-time start
   - `HF_TKN_FILE="./token"` - Add your Hugging Face Hub access token to download gated models
 

pyproject.toml

@@ -35,6 +35,7 @@ dependencies = [
     "torchaudio>=2.0.0",
     "torch>=2.0.0",
     "huggingface-hub>=0.25.0",
+    "faster-whisper>=1.2.0",
     "tqdm",
     "tiktoken",
     'triton>=2.0.0; platform_machine == "x86_64" and (sys_platform == "linux" or sys_platform == "linux2")'