forked from espnet/espnet
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
03659ca
commit 75eb357
Showing
10 changed files
with
519 additions
and
4 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,68 @@ | ||
| # This configuration requires 4 GPUs with 32GB memory | ||
| batch_type: numel | ||
| batch_bins: 6000000 | ||
| accum_grad: 3 | ||
| max_epoch: 50 | ||
| patience: none | ||
| init: xavier_uniform | ||
| best_model_criterion: | ||
| - - valid | ||
| - acc | ||
| - max | ||
| keep_nbest_models: 10 | ||
|
|
||
| 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 | ||
| pos_enc_layer_type: "rel_pos" | ||
| selfattention_layer_type: "rel_selfattn" | ||
| activation_type: "swish" | ||
| use_cnn_module: true | ||
| cnn_module_kernel: 15 | ||
|
|
||
| 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 | ||
|
|
||
| optim: adam | ||
| optim_conf: | ||
| lr: 0.002 | ||
| scheduler: warmuplr | ||
| scheduler_conf: | ||
| warmup_steps: 25000 | ||
|
|
||
| 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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,74 @@ | ||
| # This configuration requires 4 GPUs with 32GB memory | ||
| batch_type: numel | ||
| batch_bins: 6000000 | ||
| accum_grad: 3 | ||
| max_epoch: 50 | ||
| patience: none | ||
| init: xavier_uniform | ||
| best_model_criterion: | ||
| - - valid | ||
| - acc | ||
| - max | ||
| keep_nbest_models: 10 | ||
|
|
||
| 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 | ||
| pos_enc_layer_type: "rel_pos" | ||
| selfattention_layer_type: "rel_selfattn" | ||
| activation_type: "swish" | ||
| use_cnn_module: true | ||
| cnn_module_kernel: 15 | ||
|
|
||
| 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 | ||
|
|
||
| optim: adam | ||
| optim_conf: | ||
| lr: 0.002 | ||
| scheduler: warmuplr | ||
| scheduler_conf: | ||
| warmup_steps: 25000 | ||
|
|
||
| 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 | ||
|
|
||
| normalize: utterance_mvn | ||
| normalize_conf: | ||
| norm_means: true | ||
| norm_vars: false | ||
| eps: 1.0e-20 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,70 @@ | ||
| # Trained using GTX-1080ti x4. It takes about 2days. | ||
| batch_type: numel | ||
| batch_bins: 16000000 | ||
| accum_grad: 1 | ||
| max_epoch: 50 | ||
| patience: none | ||
| # The initialization method for model parameters | ||
| init: xavier_uniform | ||
| best_model_criterion: | ||
| - - valid | ||
| - acc | ||
| - max | ||
| keep_nbest_models: 10 | ||
|
|
||
| encoder: transformer | ||
| encoder_conf: | ||
| output_size: 256 | ||
| attention_heads: 4 | ||
| linear_units: 2048 | ||
| num_blocks: 12 | ||
| dropout_rate: 0.1 | ||
| positional_dropout_rate: 0.1 | ||
| attention_dropout_rate: 0.0 | ||
| input_layer: conv2d | ||
| normalize_before: true | ||
|
|
||
| decoder: transformer | ||
| decoder_conf: | ||
| attention_heads: 4 | ||
| linear_units: 2028 | ||
| num_blocks: 6 | ||
| dropout_rate: 0.1 | ||
| positional_dropout_rate: 0.1 | ||
| self_attention_dropout_rate: 0.0 | ||
| src_attention_dropout_rate: 0.0 | ||
|
|
||
| model_conf: | ||
| ctc_weight: 0.3 | ||
| lsm_weight: 0.1 | ||
| length_normalized_loss: false | ||
|
|
||
| optim: adam | ||
| optim_conf: | ||
| lr: 0.005 | ||
| 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 | ||
|
|
||
|
|
||
| normalize: utterance_mvn | ||
| normalize_conf: | ||
| norm_means: true | ||
| norm_vars: false | ||
| eps: 1.0e-20 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,70 @@ | ||
| # Trained using GTX-1080ti x4. It takes about 2days. | ||
| batch_type: numel | ||
| batch_bins: 16000000 | ||
| accum_grad: 1 | ||
| max_epoch: 50 | ||
| patience: none | ||
| # The initialization method for model parameters | ||
| init: xavier_uniform | ||
| best_model_criterion: | ||
| - - valid | ||
| - acc | ||
| - max | ||
| keep_nbest_models: 10 | ||
|
|
||
| encoder: transformer | ||
| encoder_conf: | ||
| output_size: 256 | ||
| attention_heads: 4 | ||
| linear_units: 2048 | ||
| num_blocks: 12 | ||
| dropout_rate: 0.1 | ||
| positional_dropout_rate: 0.1 | ||
| attention_dropout_rate: 0.0 | ||
| input_layer: conv2d | ||
| normalize_before: true | ||
|
|
||
| decoder: transformer | ||
| decoder_conf: | ||
| attention_heads: 4 | ||
| linear_units: 2028 | ||
| num_blocks: 6 | ||
| dropout_rate: 0.1 | ||
| positional_dropout_rate: 0.1 | ||
| self_attention_dropout_rate: 0.0 | ||
| src_attention_dropout_rate: 0.0 | ||
|
|
||
| model_conf: | ||
| ctc_weight: 0.3 | ||
| lsm_weight: 0.1 | ||
| length_normalized_loss: false | ||
|
|
||
| optim: adam | ||
| optim_conf: | ||
| lr: 0.005 | ||
| 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 | ||
|
|
||
|
|
||
| normalize: utterance_mvn | ||
| normalize_conf: | ||
| norm_means: true | ||
| norm_vars: false | ||
| eps: 1.0e-20 |
Oops, something went wrong.