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
fix(train): initialize DeepSpeed mode from resolved config (#3471)
112b80f May committed 3 months ago
Merge pull request #3467 from modelscope/codex/release-1.4.1-20260804
06c59d2 zhifu gao committed 3 months ago
docs(site): surface WhisperLiveKit SenseVoice backend (#3460)
286e382 zhifu gao committed 3 months ago
feat(nano): support LoRA finetuning of the Qwen3 LLM (#3456)
0738581 张思远 (ZhangSiYuan) committed 3 months ago
fix(trainer): avoid KeyError when a checkpoint is saved at an unvalidated step (#3455)
036ed69 张思远 (ZhangSiYuan) committed 3 months ago
Merge pull request #3450 from wangxiuwen/fix/audio-frame-copy-ownership
cb0eb3b zhifu gao committed 3 months ago
Merge pull request #3449 from wangxiuwen/fix/ffmpeg-avio-buffer-lifetime
e8b75de zhifu gao committed 3 months ago
Merge pull request #3448 from wangxiuwen/fix/tpass-buffer-lifetime
c3142f7 zhifu gao committed 3 months ago
feat(site): surface ecosystem repositories on homepage (#3446)
7eb1da3 zhifu gao committed 3 months ago