funasr1.0 streaming demo

游雁

2024-01-12 0143122a4e2ee86cc27ba137b2bb0530577cbf12

 examples/industrial_data_pretraining/paraformer_streaming/demo.py

@@ -9,11 +9,9 @@
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention

model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revison="v2.0.0")
model = AutoModel(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.0")
cache = {}
res = model(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
            cache=cache,
            is_final=True,
            chunk_size=chunk_size,
            encoder_chunk_look_back=encoder_chunk_look_back,
            decoder_chunk_look_back=decoder_chunk_look_back,
@@ -24,10 +22,8 @@
import soundfile
import os

speech, sample_rate = soundfile.read(os.path.expanduser('~')+
                                     "/.cache/modelscope/hub/damo/"+
                                     "speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/"+
                                     "example/asr_example.wav")
wav_file = os.path.join(model.model_path, "example/asr_example.wav")
speech, sample_rate = soundfile.read(wav_file)

chunk_stride = chunk_size[1] * 960 # 600ms、480ms