| | |
|---|
| | | chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms |
|---|
| | | 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="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.4") |
|---|
| | | model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="master") |
|---|
| | | |
|---|
| | | wav_file = os.path.join(model.model_path, "example/asr_example.wav") |
|---|
| | | res = model.generate(input=wav_file, |
|---|
