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: handle empty audio/text input gracefully in VAD and PUNC models
4ad2a7b 游雁 committed 6 months ago
fix: add super().__init__() to SinusoidalPositionEncoder classes; add VAD streaming test
bff79be 游雁 committed 6 months ago
perf: optimize _reset_runtime_configs to skip deepcopy of immutable objects
4bb3342 游雁 committed 6 months ago
fix: correct __int__ typo to __init__ in SinusoidalPositionEncoder
22bb089 游雁 committed 6 months ago
Add model integration tests for major models (VAD, Paraformer, SenseVoice, CAM++, CT-Transformer, Streaming)
266b8a2 zhifu.gzf committed 6 months ago
Fix #2839: initialize punc_res before conditional to prevent UnboundLocalError (#2840)
8dc6cea Lidang Jiang committed 6 months ago
Fix: prevent model graph and kwargs mutation in AutoModel.export() /修复 AutoModel 连续导出导致的计算图破坏与字典污染Fixes a critical destructive bug in `AutoModel.export()`. (#2835)
8f3314c ottercoconut committed 6 months ago
Fix #2815: apply punc_model in generate() when vad_model is not configured (#2816)
43e05d4 Daniel Bates committed 8 months ago
Fix a compatibility issue with the timestamp format for Fun-ASR-Nano-2512 (#2814)
45c74cf slin000111 committed 8 months ago
Fix #2809: remove unnecessary GPU-to-CPU transfer in VAD ComputeScores (#2817)
b6c29a6 Daniel Bates committed 8 months ago
Fix #2793: convert stereo/multi-channel audio to mono in extract_fbank (#2819)
a1bc5b5 Daniel Bates committed 8 months ago
Fix #2787: model.generate时,传入的是音频字节流,会对采样率校验耗时200ms。 (#2820)
1045123 Daniel Bates committed 8 months ago
Fix #2782: convert timestamp to int before offset addition in inference_with_vad (#2821)
5850915 Daniel Bates committed 8 months ago
fix(dataset): fix dynamic masking error in input construction (#2801)
81d96c9 roney123 committed 9 months ago
Merge branch 'main' of github.com:alibaba-damo-academy/FunASR merge
7c91e28 游雁 committed 9 months ago