Repository · GitHub

modelscope/FunASR

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

View on GitHubReport an issue

Owner	modelscope
License (as declared)	MIT
Stars	20,697
Forks	2,079
Main language	Python
Created	24 November 2022
Last updated at source	13 October 2026

pythonasraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative

Embed this entry

<iframe src="https://silytics.si/embed/item/64e01f50-bd65-432e-9084-3e417bc4bb3e" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from modelscope

ms-swiftRepository
modelscopeRepository
FunClipRepository
ClearerVoice-StudioRepository
evalscopeRepository
AgentEvolverRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.