| | |
|---|
| | | encoder_chunk_look_back = 0 #number of chunks to lookback for encoder self-attention |
|---|
| | | decoder_chunk_look_back = 0 #number of encoder chunks to lookback for decoder cross-attention |
|---|
| | | |
|---|
| | | model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming") |
|---|
| | | model = AutoModel( |
|---|
| | | model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming" |
|---|
| | | ) |
|---|
| | | cache = {} |
|---|
| | | res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", |
|---|
| | | res = model.generate( |
|---|
| | | input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", |
|---|
| | | chunk_size=chunk_size, |
|---|
| | | encoder_chunk_look_back=encoder_chunk_look_back, |
|---|
| | | decoder_chunk_look_back=decoder_chunk_look_back, |
|---|
| | |
|---|
| | | for i in range(total_chunk_num): |
|---|
| | | speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride] |
|---|
| | | is_final = i == total_chunk_num - 1 |
|---|
| | | res = model.generate(input=speech_chunk, |
|---|
| | | res = model.generate( |
|---|
| | | input=speech_chunk, |
|---|
| | | cache=cache, |
|---|
| | | is_final=is_final, |
|---|
| | | chunk_size=chunk_size, |
|---|
