| | |
|---|
| | | chunk_size = [5, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms |
|---|
| | | 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 |
|---|
| | | |
|---|
| | | wav_file="/Users/zhifu/Downloads/NCYzUhAtZNI_0015.wav" |
|---|
| | | model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.4") |
|---|
| | | 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=wav_file, |
|---|
| | | chunk_size=chunk_size, |
|---|
| | | encoder_chunk_look_back=encoder_chunk_look_back, |
|---|
| | | decoder_chunk_look_back=decoder_chunk_look_back, |
|---|
| | | ) |
|---|
| | | print(res) |
|---|
| | | |
|---|
| | | # exit() |
|---|
| | | |
|---|
| | | import soundfile |
|---|
| | | import os |
|---|
| | | |
|---|
| | | wav_file = os.path.join(model.model_path, "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 |
|---|
