| | |
|---|
| | | dataset: AudioDataset |
|---|
| | | dataset_conf: |
|---|
| | | index_ds: IndexDSJsonl |
|---|
| | | batch_sampler: DynamicBatchLocalShuffleSampler |
|---|
| | | batch_type: example # example or length |
|---|
| | | batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len; |
|---|
| | | batch_sampler: EspnetStyleBatchSampler |
|---|
| | | batch_type: length # example or length |
|---|
| | | batch_size: 10000 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len; |
|---|
| | | max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length, |
|---|
| | | buffer_size: 500 |
|---|
| | | buffer_size: 1024 |
|---|
| | | shuffle: True |
|---|
| | | num_workers: 4 |
|---|
| | | preprocessor_speech: SpeechPreprocessSpeedPerturb |
|---|
| | | preprocessor_speech_conf: |
|---|
| | | speed_perturb: [0.9, 1.0, 1.1] |
|---|
| | | |
|---|
| | | tokenizer: CharTokenizer |
|---|
| | | tokenizer_conf: |
|---|
| | | unk_symbol: <unk> |
|---|
| | | split_with_space: true |
|---|
| | | |
|---|
| | | |
|---|
| | | ctc_conf: |
|---|
