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: support loading .pcm (16k 1c 16bit) audio files in load_utils.py (#2667) (#2668)
eb1574b weilikai committed 1 year ago
Fix prefix concatenation in timestamp post-processing for sensevoice (#2670)
88b464e slin000111 committed 1 year ago
examples: add improved batch_asr CLI example with error handling (#2675)
e175dae Anjali Barge committed 1 year ago
docs(readme): update onnx example import path and cache location (#2607)
8316fc4 Jeffrey Guan committed 1 year ago
Fix: 修复c++后端服务因为空数组的异常退出,以及c++的http服务在收到Ctrl+C信号后无法正常退出 (#2571)
05c8eba nianjiuhuiyi committed 1 year ago
feat: add 'words' key aligned with timestamps in sensevoice model output (#2531)
8b0fb74 chengligen committed 1 year ago
fix: msg_stamp.size() is unsigned,should convert to int (#2523)
eccf746 TouchZZZ committed 1 year ago
fix bug for core dump in http, use libboost as parse (#2509)
ae013cf zhaomingwork committed 1 year ago