| | |
|---|
| | | 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_revision="v2.0.2") |
|---|
| | | model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/speech_SCAMA_asr-zh-cn-16k-common-vocab8358-streaming", model_revision="v2.0.4") |
|---|
| | | cache = {} |
|---|
| | | 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, |
|---|
