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 |
|---|---|---|
| .. | ||
| auto | ||
| bin | ||
| datasets | ||
| download | ||
| frontends | ||
| losses | ||
| metrics | ||
| models | ||
| optimizers | ||
| schedulers | ||
| tokenizer | ||
| train_utils | ||
| utils | ||
| __init__.py 3.1 KB | ||
| cli.py 25.3 KB | ||
| register.py 3.1 KB | ||
| version.txt 7 B | ||