F
FunASR
modelscope/FunASR
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
★19.7kstars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Models category, core strengths: asr/audio
Who made it?Maintained by modelscope team, 19.7K⭐ on GitHub, #71 out of 3201 in Models
Why does it exist?In the Models space, asr workflows faced efficiency bottlenecks. FunASR was built by modelscope to address these audio challenges.
What can it do?Key use cases: chinese, emotion-recognition, funasr
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/modelscope/FunASR | 官网 www.funasr.com
🔗 github.com/modelscope/FunASR | 官网 www.funasr.com
Topics
asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative