xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 20:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Doc] Fix Markdown Pre-commit Error (#24670)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-09-11 12:05:59 -04:00 committed by GitHub
parent 404c85ca72
commit 4984a291d5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
docs/contributing/model/transcription.md
View File

@ -37,7 +37,7 @@ It is assumed you have already implemented your model in vLLM according to the b
- The `supported_languages` mapping is validated at init time.
- Set `supports_transcription_only=True` if the model should not serve text generation (eg Whisper).
- Provide an ASR configuration via [get_speech_to_text_config][vllm.model_executor.models.interfaces.SupportsTranscription.get_speech_to_text_config].
- Provide an ASR configuration via [get_speech_to_text_config][vllm.model_executor.models.interfaces.SupportsTranscription.get_speech_to_text_config].
This is for controlling general behavior of the API when serving your model:
??? code
@ -65,7 +65,7 @@ It is assumed you have already implemented your model in vLLM according to the b
- Implement the prompt construction via [get_generation_prompt][vllm.model_executor.models.interfaces.SupportsTranscription.get_generation_prompt]. The server passes you the resampled waveform and task parameters; you return a valid [PromptType][vllm.inputs.data.PromptType]. There are two common patterns:
#### A. Multimodal LLM with audio embeddings (e.g., Voxtral, Gemma3n)
### A. Multimodal LLM with audio embeddings (e.g., Voxtral, Gemma3n)
Return a dict containing `multi_modal_data` with the audio, and either a `prompt` string or `prompt_token_ids`:
@ -102,7 +102,7 @@ It is assumed you have already implemented your model in vLLM according to the b
For further clarification on multi modal inputs, please refer to [Multi-Modal Inputs](../../features/multimodal_inputs.md).
#### B. Encoder–decoder audio-only (e.g., Whisper)
### B. Encoder–decoder audio-only (e.g., Whisper)
Return a dict with separate `encoder_prompt` and `decoder_prompt` entries:
@ -142,7 +142,6 @@ It is assumed you have already implemented your model in vLLM according to the b
return cast(PromptType, prompt)
```
- (Optional) Language validation via [validate_language][vllm.model_executor.models.interfaces.SupportsTranscription.validate_language]
If your model requires a language and you want a default, override this method (see Whisper):
@ -177,7 +176,6 @@ It is assumed you have already implemented your model in vLLM according to the b
return int(audio_duration_s * stt_config.sample_rate // 320) # example
```
## 2. Audio preprocessing and chunking
The API server takes care of basic audio I/O and optional chunking before building prompts:
@ -264,10 +262,11 @@ Once your model implements `SupportsTranscription`, you can test the endpoints (
-F "model=$MODEL_ID" \
http://localhost:8000/v1/audio/translations
```
Or check out more examples in <gh-file:examples/online_serving>.
!!! note
- If your model handles chunking internally (e.g., via its processor or encoder), set `min_energy_split_window_size=None` in the returned `SpeechToTextConfig` to disable server-side chunking.
- Implementing `get_num_audio_tokens` improves accuracy of streaming usage metrics (`prompt_tokens`) without an extra forward pass.
- For multilingual behavior, keep `supported_languages` aligned with actual model capabilities.
- For multilingual behavior, keep `supported_languages` aligned with actual model capabilities.