Feature request: Add FunASR/SenseVoice as audio model backend

[LauraGPT]

Summary

Xinference supports various LLM/embedding/image/audio models. Would you consider adding FunASR models (SenseVoice, Paraformer, Fun-ASR-Nano) as audio/speech model backends?

Why FunASR?

FunASR is the most popular open-source ASR toolkit for Chinese and multilingual speech recognition:

• SenseVoice (234M params): Non-autoregressive, ~25x faster than Whisper-large, 50+ languages, emotion + audio event detection
• Paraformer (220M params): ~170x realtime on GPU for Chinese, built-in VAD + punctuation
• Fun-ASR-Nano (800M params): LLM-based ASR (SenseVoice encoder + Qwen3-0.6B decoder), 31 languages
• cam++: Speaker diarization model (7.2M params)

Integration

FunASR already provides an OpenAI-compatible API server:

pip install funasr vllm
funasr-server --device cuda
# http://localhost:8000/v1/audio/transcriptions

This could serve as a reference for integrating into Xinference's model serving framework.

Model ecosystem

Model	Task	Params	Speed
SenseVoice-Small	ASR + emotion	234M	~25x vs Whisper
Paraformer-large	Chinese ASR	220M	~170x realtime
Fun-ASR-Nano	Multilingual ASR	800M	LLM-based
FSMN-VAD	Voice Activity Detection	0.4M	—
CT-Punc	Punctuation	—	—
cam++	Speaker Diarization	7.2M	—

All models available on ModelScope and HuggingFace (FunAudioLLM org).

References

• FunASR: https://github.com/modelscope/FunASR (16K+ stars)
• SenseVoice: https://github.com/FunAudioLLM/SenseVoice (8.3K+ stars)
• Install: pip install funasr

[qinxuye]

funasr is supported already. https://github.com/xorbitsai/inference/blob/main/xinference/model/audio/funasr.py

[LauraGPT]

Great to know! Thanks for pointing out the existing integration. 🙏

For anyone looking to use it:

• xinference FunASR integration

We'll link to Xinference from the FunASR ecosystem page as well.