Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
Commits on main
Merge pull request #3217 from modelscope/codex/refresh-growth-ops-batch-20260714
0643c7b zhifu gao committed 4 months ago
Merge pull request #3216 from modelscope/codex/fix-mcp-stdio-transport-20260714
3b146a3 zhifu gao committed 4 months ago
fix: bound realtime websocket state for long sessions (#3214)
a53497b zhifu gao committed 4 months ago
fix: disable timestamps when CTC weights are missing (#3211)
aefddc1 zhifu gao committed 4 months ago
fix: accept float32 dtype in realtime websocket server (#3204)
505455e zhifu gao committed 4 months ago
Merge pull request #3201 from modelscope/codex/glama-metadata-20260710
b1a7283 zhifu gao committed 4 months ago
Merge pull request #3200 from modelscope/codex/track-linly-talker-funasr-link-20260708
701cef4 zhifu gao committed 4 months ago
Merge pull request #3199 from modelscope/codex/track-1c7-funclip-link-refresh-20260708
baa27a7 zhifu gao committed 4 months ago