Live transcription · Multilingual

SenseVoice Small

Fast multilingual speech recognition from FunAudioLLM — non-autoregressive SenseVoice, tuned for Chinese, Cantonese, English, Japanese and Korean

Multilingual · 5.6× · 448.4 MB

Install in OpenASR Desktop

Opens the desktop app and downloads this model for you.

Don't have the app yet? Download OpenASR Desktop

On-deviceOn this computer
interview.m4a12:04

let's line up this week's release plan,

the beta build can ship on Friday,

then loop in design and QA,

Why it fits

SenseVoice Small is the compact member of SenseVoice, the speech understanding model family open-sourced by FunAudioLLM (Alibaba). Trained on more than 400,000 hours of speech, it delivers high-precision transcription with automatic language detection for Mandarin Chinese, Cantonese, English, Japanese and Korean, and the upstream card reports Chinese and Cantonese accuracy ahead of Whisper on open benchmarks such as AISHELL and WenetSpeech. Its non-autoregressive end-to-end architecture makes inference exceptionally fast — the upstream team clocks about 70 ms for 10 seconds of audio, 15x faster than Whisper-Large. The upstream model also carries speech emotion recognition and audio event detection; the OpenASR packs currently surface plain transcription only (emotion/event tags are not yet exposed). This OpenASR repo repackages the original weights as .oasr packs that run natively in the OpenASR runtime — no Python at inference time. The fp16 build is the recommended default for maximum fidelity; q8_0 halves the footprint at near-reference quality and q4_k suits tight-memory devices.

What you can do with it

  • 🌏 Multilingual, zh-first — high-precision Mandarin, Cantonese, English, Japanese and Korean with automatic language detection
  • Non-autoregressive speed — an end-to-end architecture the upstream clocks at about 70 ms for 10 seconds of audio, 15 times faster than Whisper-Large
  • 🀄 Chinese benchmark strength — trained on over 400,000 hours of speech; the upstream reports better Chinese and Cantonese accuracy than Whisper on AISHELL and WenetSpeech
  • 🪶 Compact and local — a small checkpoint that transcribes fully offline, from a 130 MB q4_k build up to full-fidelity fp16
  • 🦀 Native in OpenASR.oasr packs run with no Python at inference, engineered for peak performance on CPU & GPU

Other models

Developer details CLI commands, file hashes, and per-quant downloads — for scripting and verification.

Downloads by quantization

Pull stringSizeQuant
sensevoice-small:fp16default 448.4 MB fp16
open .oasr
sensevoice-small:q8 240.8 MB q8_0
open .oasr
sensevoice-small:q4 130 MB q4_k
open .oasr

Model facts

Size448.4 MB
Speed5.6× real-time
LanguageMultilingual
Familysensevoice
VendorFunAudioLLM
Released2024-07-04
Peak memory710 MB
Quantizationfp16
Revision52fa74567f213c8280fbea6e2d919709b7a7209f
sha25697a59d7cd080731a1972fc87fd089b3cccfd20ca77ce5bc3e90d54a8d0802ea7

Usage

These are CLI / local-server examples. The desktop app runs this model without typing a command — use Install above.

bash · transcribe a file
$ openasr pull sensevoice-small:fp16
↓ sensevoice-small.oasr  448.4 MB  ✓ verified sha256
$ openasr transcribe meeting.wav --backend native --model-pack ~/.openasr/models/sensevoice-small/fp16/sensevoice-small-fp16.oasr
✓ local transcript · 0 bytes sent
bash · serve a local API
$ openasr serve --backend native --model-pack ~/.openasr/models/sensevoice-small/fp16/sensevoice-small-fp16.oasr --addr 127.0.0.1:8080
▶ http://127.0.0.1:8080 · model=sensevoice-small · 0 bytes will leave this host
python · client.py
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:8080/v1", api_key="local")
audio = open("meeting.wav", "rb")
text = client.audio.transcriptions.create(model="sensevoice-small", file=audio)