sensevoice

游雁

2024-07-16 f0eec4c4da6c4a7fb16bebbda9a928d94b93fd1c

 examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py

@@ -9,11 +9,9 @@

model = AutoModel(model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch")

mm = model.model
for p in mm.parameters():
    print(f"{p.numel()}")
res = model.generate(input=wav_file)
print(res)

# [[beg1, end1], [beg2, end2], .., [begN, endN]]
# beg/end: ms