Skip to content

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

955 B
Raw Blame

Contributing to FunASR

Thanks for taking the time to contribute to FunASR.

The canonical contribution guide is now CONTRIBUTING.md. It covers the development setup, high-impact contribution areas, validation expectations, pull request checklist, and issue-reporting guidance.

Quick links

Maintainer priorities

The most valuable contributions help new users reach a successful transcription quickly, make private deployment easier, or make benchmark results easier to reproduce.