| New file |
| | |
|---|
| | | # network architecture |
|---|
| | | # encoder related |
|---|
| | | encoder: conformer |
|---|
| | | encoder_conf: |
|---|
| | | output_size: 512 # dimension of attention |
|---|
| | | attention_heads: 8 |
|---|
| | | linear_units: 2048 # the number of units of position-wise feed forward |
|---|
| | | num_blocks: 12 # the number of encoder blocks |
|---|
| | | dropout_rate: 0.1 |
|---|
| | | positional_dropout_rate: 0.1 |
|---|
| | | attention_dropout_rate: 0.0 |
|---|
| | | input_layer: conv2d # encoder architecture type |
|---|
| | | normalize_before: true |
|---|
| | | rel_pos_type: latest |
|---|
| | | pos_enc_layer_type: rel_pos |
|---|
| | | selfattention_layer_type: rel_selfattn |
|---|
| | | activation_type: swish |
|---|
| | | macaron_style: true |
|---|
| | | use_cnn_module: true |
|---|
| | | cnn_module_kernel: 15 |
|---|
| | | |
|---|
| | | # decoder related |
|---|
| | | decoder: transformer |
|---|
| | | decoder_conf: |
|---|
| | | attention_heads: 8 |
|---|
| | | linear_units: 2048 |
|---|
| | | num_blocks: 6 |
|---|
| | | dropout_rate: 0.1 |
|---|
| | | positional_dropout_rate: 0.1 |
|---|
| | | self_attention_dropout_rate: 0.0 |
|---|
| | | src_attention_dropout_rate: 0.0 |
|---|
| | | |
|---|
| | | # CTC realted |
|---|
| | | ctc_conf: |
|---|
| | | ignore_nan_grad: true |
|---|
| | | |
|---|
| | | # frontend related |
|---|
| | | frontend: wav_frontend |
|---|
| | | frontend_conf: |
|---|
| | | fs: 16000 |
|---|
| | | window: hamming |
|---|
| | | n_mels: 80 |
|---|
| | | frame_length: 25 |
|---|
| | | frame_shift: 10 |
|---|
| | | lfr_m: 1 |
|---|
| | | lfr_n: 1 |
|---|
| | | |
|---|
| | | # hybrid CTC/attention |
|---|
| | | model_conf: |
|---|
| | | ctc_weight: 0.3 |
|---|
| | | lsm_weight: 0.1 # label smoothing option |
|---|
| | | length_normalized_loss: false |
|---|
| | | |
|---|
| | | # optimization related |
|---|
| | | accum_grad: 4 |
|---|
| | | grad_clip: 5 |
|---|
| | | patience: none |
|---|
| | | max_epoch: 30 |
|---|
| | | val_scheduler_criterion: |
|---|
| | | - valid |
|---|
| | | - acc |
|---|
| | | best_model_criterion: |
|---|
| | | - - valid |
|---|
| | | - acc |
|---|
| | | - max |
|---|
| | | keep_nbest_models: 10 |
|---|
| | | |
|---|
| | | optim: adam |
|---|
| | | optim_conf: |
|---|
| | | lr: 0.0015 |
|---|
| | | scheduler: warmuplr |
|---|
| | | scheduler_conf: |
|---|
| | | warmup_steps: 30000 |
|---|
| | | |
|---|
| | | specaug: specaug |
|---|
| | | specaug_conf: |
|---|
| | | apply_time_warp: true |
|---|
| | | time_warp_window: 5 |
|---|
| | | time_warp_mode: bicubic |
|---|
| | | apply_freq_mask: true |
|---|
| | | freq_mask_width_range: |
|---|
| | | - 0 |
|---|
| | | - 30 |
|---|
| | | num_freq_mask: 2 |
|---|
| | | apply_time_mask: true |
|---|
| | | time_mask_width_range: |
|---|
| | | - 0 |
|---|
| | | - 40 |
|---|
| | | num_time_mask: 2 |
|---|
| | | |
|---|
| | | dataset_conf: |
|---|
| | | data_names: speech,text |
|---|
| | | data_types: sound,text_nospace |
|---|
| | | shuffle: True |
|---|
| | | shuffle_conf: |
|---|
| | | shuffle_size: 2048 |
|---|
| | | sort_size: 500 |
|---|
| | | batch_conf: |
|---|
| | | batch_type: token |
|---|
| | | batch_size: 32000 |
|---|
| | | num_workers: 8 |
|---|
| | | |
|---|
| | | log_interval: 50 |
|---|
| | | normalize: None |
|---|
