| | |
|---|
| | | import soundfile |
|---|
| | | speech, sample_rate = soundfile.read("example/asr_example.wav") |
|---|
| | | |
|---|
| | | chunk_size = [0, 10, 5] #[5, 10, 5] 600ms, [8, 8, 4] 480ms |
|---|
| | | 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 |
|---|
| | | param_dict = {"cache": dict(), "is_final": False, "chunk_size": chunk_size, |
|---|
| | |
|---|
| | | if __name__ == '__main__': |
|---|
| | | params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", data_path="./data") |
|---|
| | | params.output_dir = "./checkpoint" # m模型保存路径 |
|---|
| | | params.data_path = "./example_data/" # 数据路径 |
|---|
| | | params.data_path = "speech_asr_aishell1_trainsets" # 数据路径 |
|---|
| | | params.dataset_type = "small" # 小数据量设置small，若数据量大于1000小时，请使用large |
|---|
| | | params.batch_bins = 2000 # batch size，如果dataset_type="small"，batch_bins单位为fbank特征帧数，如果dataset_type="large"，batch_bins单位为毫秒， |
|---|
| | | params.max_epoch = 20 # 最大训练轮数 |
|---|
