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
Update model.py to fix "IndexError: index 1 is out of bounds for dimension 1 with size 0" (#2454)
3df109a Isuxiz Slidder committed 1 year ago
1. bug fix:list(mean)和list(var),由于mean和var是numpy,导致写入到文件的格式错误,参考上面的话,大概率是list(mean.tolist()),其实外层list没有必要 (#2437)
6e69d78 天地 committed 1 year ago
fix: use converted token_ids for alignment for sensevoice model with timestamp output (#2429)
3c349ac Han Zhang committed 1 year ago
Merge pull request #2418 from modelscope/revert-2382-dev_clean
027ad5c Shi Xian committed 1 year ago
修复 当选用SenseVoice模型处理长音频(同时开启vad和output_timestamp)时的异常 (#2413)
6fe10a8 hohaiuhsx committed 1 year ago
fix: resolve CPU runtime error introduced by previous commit (c1e365f) (#2375)
6ebf6e4 BienBoy committed 1 year ago
fix: resolve unexpected 'out of memory' issue in multi-GPU setup (#2373)
c1e365f BienBoy committed 1 year ago