| New file |
| | |
| | | encoder: conformer |
| | | encoder_conf: |
| | | output_size: 512 |
| | | attention_heads: 8 |
| | | linear_units: 2048 |
| | | num_blocks: 12 |
| | | dropout_rate: 0.1 |
| | | positional_dropout_rate: 0.1 |
| | | attention_dropout_rate: 0.1 |
| | | input_layer: conv2d |
| | | normalize_before: true |
| | | macaron_style: true |
| | | rel_pos_type: latest |
| | | pos_enc_layer_type: rel_pos |
| | | selfattention_layer_type: rel_selfattn |
| | | activation_type: swish |
| | | use_cnn_module: true |
| | | cnn_module_kernel: 31 |
| | | |
| | | 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: 0.1 |
| | | src_attention_dropout_rate: 0.1 |
| | | |
| | | model_conf: |
| | | ctc_weight: 0.3 |
| | | lsm_weight: 0.1 |
| | | length_normalized_loss: false |
| | | |
| | | accum_grad: 2 |
| | | max_epoch: 50 |
| | | patience: none |
| | | init: none |
| | | best_model_criterion: |
| | | - - valid |
| | | - acc |
| | | - max |
| | | keep_nbest_models: 10 |
| | | |
| | | optim: adam |
| | | optim_conf: |
| | | lr: 0.0025 |
| | | weight_decay: 0.000001 |
| | | scheduler: warmuplr |
| | | scheduler_conf: |
| | | warmup_steps: 40000 |
| | | |
| | | 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 |
| | | - 27 |
| | | num_freq_mask: 2 |
| | | apply_time_mask: true |
| | | time_mask_width_ratio_range: |
| | | - 0. |
| | | - 0.05 |
| | | num_time_mask: 10 |
| | | |
| | | dataset_conf: |
| | | shuffle: True |
| | | shuffle_conf: |
| | | shuffle_size: 1024 |
| | | sort_size: 500 |
| | | batch_conf: |
| | | batch_type: token |
| | | batch_size: 10000 |
| | | num_workers: 8 |
| | | |
| | | log_interval: 50 |
| | | normalize: None |