GitHub repo

modelscope/FunASR

Python Tracked since 2022-11-24 Updated 2026-07-16 View source ↗

#135 of 783 by Stars among GitHub repos

19.3k Stars

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

About

Industrial speech recognition toolkit for offline, streaming, and edge deployment.

No local setup? Open the Colab quickstart to transcribe a public sample or upload your own audio in a browser.

Flagship model — Fun-ASR-Nano (LLM-ASR for Chinese, English, and Japanese, plus Chinese dialect groups and regional accents; needs a GPU):

For the separate 31-language checkpoint, use Fun-ASR-MLT-Nano-2512. Language coverage is checkpoint-specific, so Nano and MLT-Nano should be treated as distinct model choices.

On CPU (or for five-language ASR plus emotion and audio-event tags), use SenseVoiceSmall. The pipeline below composes SenseVoiceSmall with FSMN-VAD and CAM++; diarization is provided by…

Excerpted from github.com/modelscope/FunASR

Latest metrics

Stars 19.3k 2026-07-16
Forks 1.9k 2026-07-16
Commits 5.3k 2026-07-16
Releases 19 2026-07-16
Watchers 117 2026-07-16
Open issues 2 2026-07-16
Open PRs 1 2026-07-16