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
vad conf
游雁0df5eb2fdf81
diff --git a/examples/industrial_data_pretraining/emotion2vec/demo.py b/examples/industrial_data_pretraining/emotion2vec/demo.pyindex 940b9f932..510e6e861 100644--- a/examples/industrial_data_pretraining/emotion2vec/demo.py+++ b/examples/industrial_data_pretraining/emotion2vec/demo.py@@ -9,7 +9,7 @@ from funasr import AutoModelmodel = AutoModel(model="iic/emotion2vec_base_finetuned", model_revision="v2.0.4",# vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",# vad_model_revision="v2.0.4",- # vad_kwargs={"max_single_segment_time": 1000},+ # vad_kwargs={"max_single_segment_time": 2000},)wav_file = f"{model.model_path}/example/test.wav"