| | |
|---|
| | | pos_enc_class: SinusoidalPositionEncoder |
|---|
| | | normalize_before: true |
|---|
| | | kernel_size: 11 |
|---|
| | | sanm_shfit: 0 |
|---|
| | | sanm_shift: 0 |
|---|
| | | selfattention_layer_type: sanm |
|---|
| | | |
|---|
| | | # decoder |
|---|
| | |
|---|
| | | src_attention_dropout_rate: 0.1 |
|---|
| | | att_layer_num: 16 |
|---|
| | | kernel_size: 11 |
|---|
| | | sanm_shfit: 0 |
|---|
| | | sanm_shift: 0 |
|---|
| | | |
|---|
| | | # seaco decoder |
|---|
| | | seaco_decoder: ParaformerSANMDecoder |
|---|
| | |
|---|
| | | self_attention_dropout_rate: 0.1 |
|---|
| | | src_attention_dropout_rate: 0.1 |
|---|
| | | kernel_size: 21 |
|---|
| | | sanm_shfit: 0 |
|---|
| | | sanm_shift: 0 |
|---|
| | | use_output_layer: false |
|---|
| | | wo_input_layer: true |
|---|
| | | |
|---|
| | | predictor: CifPredictorV2 |
|---|
| | | predictor: CifPredictorV3 |
|---|
| | | predictor_conf: |
|---|
| | | idim: 512 |
|---|
| | | threshold: 1.0 |
|---|
| | | l_order: 1 |
|---|
| | | r_order: 1 |
|---|
| | | tail_threshold: 0.45 |
|---|
| | | smooth_factor2: 0.25 |
|---|
| | | noise_threshold2: 0.01 |
|---|
| | | upsample_times: 3 |
|---|
| | | use_cif1_cnn: false |
|---|
| | | upsample_type: cnn_blstm |
|---|
| | | |
|---|
| | | # frontend related |
|---|
| | | frontend: WavFrontend |
|---|
| | |
|---|
| | | dataset: AudioDataset |
|---|
| | | dataset_conf: |
|---|
| | | index_ds: IndexDSJsonl |
|---|
| | | batch_sampler: DynamicBatchLocalShuffleSampler |
|---|
| | | batch_sampler: BatchSampler |
|---|
| | | 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; |
|---|
| | | max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length, |
|---|
