update readme, fix seaco bug

shixian.shi

2024-01-15 55c09aeaa25b4bb88a50e09ba68fa6ff00a6d676

 examples/industrial_data_pretraining/fsmn_vad_streaming/demo.py

@@ -7,11 +7,9 @@
wav_file = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav"

chunk_size = 60000 # ms
model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_fsmn_vad_zh-cn-16k-common-streaming", model_revision="v2.0.0")
model = AutoModel(model="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch", model_revision="v2.0.2")

res = model(input=wav_file,
            chunk_size=chunk_size,
            )
res = model(input=wav_file, chunk_size=chunk_size, )
print(res)


@@ -22,16 +20,18 @@
wav_file = os.path.join(model.model_path, "example/vad_example.wav")
speech, sample_rate = soundfile.read(wav_file)

chunk_stride = int(chunk_size * 16000 / 1000)
chunk_stride = int(chunk_size * sample_rate / 1000)

cache = {}

for i in range(int(len((speech)-1)/chunk_stride+1)):
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
for i in range(total_chunk_num):
    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
    is_final = i == int(len((speech)-1)/chunk_stride+1) - 1
    is_final = i == total_chunk_num - 1
    res = model(input=speech_chunk,
                cache=cache,
                is_final=is_final,
                chunk_size=chunk_size,
                )
    print(res)
    if len(res[0]["value"]):
        print(res)