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
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| normalizers | ||
| __init__.py 6.8 KB | ||
| __main__.py 40 B | ||
| audio.py 4.8 KB | ||
| decoding.py 40.1 KB | ||
| model.py 19.7 KB | ||
| timing.py 12.8 KB | ||
| tokenizer.py 16.1 KB | ||
| transcribe.py 28.7 KB | ||
| triton_ops.py 3.8 KB | ||
| utils.py 13.9 KB | ||
| version.py 25 B | ||