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
docs: add vLLM repeated punctuation troubleshooting (#3118)
a6ebdb7 zhifu gao committed 4 months ago
Migrate editdistance metrics to rapidfuzz with empty-reference guard
cd15a47 zhifu gao committed 4 months ago
feat: add postprocess hotword correction for AutoModel.generate() (#2959)
76a3e71 li xuanqun committed 4 months ago
fix(tokenizer): treat special-token strings as text to prevent batch crashes (#3110)
57e2f48 liuweiqing committed 4 months ago
Document realtime WS partial rendering and concurrency (#3092)
4a412f8 zhifu gao committed 4 months ago