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(runtime): release ONNX VAD and punctuation fixes as 0.4.9 (#3850)
60adaf8 zhifu gao committed 13 days ago
fix(runtime): release ONNX VAD and punctuation fixes as 0.4.9
cd6e169 zhifu gao committed 13 days ago
fix(onnx): preserve punctuation state on empty input (#3847)
49f7472 zhifu gao committed 13 days ago
fix(onnx): handle empty and short offline VAD inputs (#3846)
d8e6766 zhifu gao committed 13 days ago
fix(frontend): handle default no-LFR online features (#3849)
57485f7 zhifu gao committed 13 days ago
fix(onnx): handle empty punctuation input without consuming cache
190ff6e BillVan1945 committed 13 days ago
fix(onnx): handle offline VAD inputs without feature frames
f2dfafb BillVan1945 committed 14 days ago
fix(runtime): release Torch CMVN parser fix as 0.1.6 (#3844)
fd1d4aa zhifu gao committed 14 days ago
fix(runtime): release Torch hotword batching fix as 0.1.5 (#3840)
baefd3b zhifu gao committed 14 days ago
fix(runtime): release ONNX hotword batching fix as 0.4.7 (#3839)
04e6fb6 zhifu gao committed 15 days ago
fix(runtime): preserve hotword embeddings across input batches (#3838)
50c3b97 zhifu gao committed 15 days ago
fix(runtime): decode every batch in ContextualParaformer and SeacoParaformer
fe89f75 Tanishq committed 16 days ago