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
sensevoice
游雁774caaf75222
diff --git a/README.md b/README.mdindex 4638ab36e..3a99b99e5 100644--- a/README.md+++ b/README.md@@ -129,6 +129,34 @@ funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++inpNotes: Support recognition of single audio file, as well as file list in Kaldi-style wav.scp format: `wav_id wav_pat`### Speech Recognition (Non-streaming)+#### SenseVoice+```python+from funasr import AutoModel+from funasr.utils.postprocess_utils import rich_transcription_postprocess++model_dir = "iic/SenseVoiceSmall"++model = AutoModel(+ model=model_dir,+ vad_model="fsmn-vad",+ vad_kwargs={"max_single_segment_time": 30000},+ device="cuda:0",+)++# en+res = model.generate(+ input=f"{model.model_path}/example/en.mp3",+ cache={},+ language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ use_itn=True,+ batch_size_s=60,+ merge_vad=True, #+ merge_length_s=15,+)+text = rich_transcription_postprocess(res[0]["text"])+print(text)+```+#### Paraformer```pythonfrom funasr import AutoModel# paraformer-zh is a multi-functional asr modeldiff --git a/README_zh.md b/README_zh.mdindex 275a30d6f..70a6d25b8 100644--- a/README_zh.md+++ b/README_zh.md@@ -128,6 +128,34 @@ funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++inp注:支持单条音频文件识别,也支持文件列表,列表为kaldi风格wav.scp:`wav_id wav_path`### 非实时语音识别+#### SenseVoice+```python+from funasr import AutoModel+from funasr.utils.postprocess_utils import rich_transcription_postprocess++model_dir = "iic/SenseVoiceSmall"++model = AutoModel(+ model=model_dir,+ vad_model="fsmn-vad",+ vad_kwargs={"max_single_segment_time": 30000},+ device="cuda:0",+)++# en+res = model.generate(+ input=f"{model.model_path}/example/en.mp3",+ cache={},+ language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ use_itn=True,+ batch_size_s=60,+ merge_vad=True, #+ merge_length_s=15,+)+text = rich_transcription_postprocess(res[0]["text"])+print(text)+```+#### Paraformer```pythonfrom funasr import AutoModel# paraformer-zh is a multi-functional asr model