Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

vad conf

游雁0df5eb2fdf81
diff --git a/examples/industrial_data_pretraining/emotion2vec/demo.py b/examples/industrial_data_pretraining/emotion2vec/demo.py
index 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 AutoModel
model = 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"