From: modelscope <github.com/modelscope>Newsgroups: alt.freeweights.toolsSubject:

FunASR

Release: v1.4.26 (2026-11-12)Commit: cdd82b5License: MIT

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

speechv1.4.26releaseFunASRPythonMIT
FactsLicenseMITLanguagePythonKindspeechRelease2026-11-12PlatformsLinux, macOS, WindowsLinks to the projectpermissive
$ pip install funasr

Overview

Speech recognition toolkit with voice activity detection and punctuation.

Kind
speech
License
MIT
Language
Python
Platforms
Linux, macOS, Windows
Latest release
v1.4.26 (2026-11-12)
Repository
modelscope/FunASR
Topicsasraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asr

Freeweights links to the project and does not host tool binaries.

Install

$ pip install funasr
$ pip install funasr

Checked against the project's README on 2026-11-15. The project's own instructions win when they differ: install docs

Freeweights links to the project and does not host tool binaries.

Use with Freeweights

Run a catalog model

Download the weights from Freeweights first (HF_ENDPOINT or fw.py), then point the tool at the folder.

Catalog models it can run (189)

and 129 more.

License

License
MIT
Class
Permissive

Read the license

Freeweights links to the project and does not host tool binaries.

Provenance

From: modelscope <github.com/modelscope>Newsgroups: alt.freeweights.toolsSubject: FunASRRelease: v1.4.26 (2026-11-12)Commit: cdd82b5License: MIT
Repository
modelscope/FunASR
Pinned release
v1.4.26, 2026-11-12
Release commit
cdd82b5cbfd05015f8fb2b167d61f25142c3a9e8
Default branch
main c2107cdd3d025c449020c05b0eadd746345f4f03
Fetched
2026-11-15
Takedowns
None.

Freeweights links to the project and does not host tool binaries.

Works with

189 catalog models. See the list