Skip to content

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

Commits on main

9bdce64
docs: align multilingual model and serving guides
zhifu gao committed 2 months ago
3cefbe5
docs: add speaker and emotion task guides
zhifu gao committed 2 months ago
f4c5d93
beb92d9
f85d8f5
docs: add bilingual streaming VAD task guide
zhifu gao committed 2 months ago
3ac13e5
Merge pull request #3653: preserve API signatures
zhifu gao committed 2 months ago
fe719c0
f0728b7