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
Showing
4 changed files
with
156 additions
and
0 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 +1,6 @@ | ||
| beam_size: 20 | ||
| ctc_weight: 0.3 | ||
| lm_weight: 0.0 | ||
| maxlenratio: 0.0 | ||
| minlenratio: 0.0 | ||
| penalty: 0.0 |
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 +1,77 @@ | ||
| # Trained with NVIDIA A40 GPU (48GB) x 2 | ||
| encoder: conformer | ||
| encoder_conf: | ||
| output_size: 256 | ||
| attention_heads: 4 | ||
| linear_units: 1024 | ||
| 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: 4 | ||
| 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 | ||
|
|
||
| frontend_conf: | ||
| n_fft: 512 | ||
| win_length: 400 | ||
| hop_length: 160 | ||
|
|
||
| seed: 2022 | ||
| use_amp: true | ||
| num_workers: 6 | ||
| batch_type: numel | ||
| batch_bins: 50000000 | ||
| accum_grad: 1 | ||
| max_epoch: 50 | ||
| init: none | ||
| best_model_criterion: | ||
| - - valid | ||
| - acc | ||
| - max | ||
| keep_nbest_models: 10 | ||
|
|
||
| optim: adam | ||
| optim_conf: | ||
| lr: 0.002 | ||
| weight_decay: 0.000001 | ||
| scheduler: warmuplr | ||
| scheduler_conf: | ||
| warmup_steps: 15000 | ||
|
|
||
| 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: 5 |
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 +1,33 @@ | ||
| #!/usr/bin/env bash | ||
| # Set bash to 'debug' mode, it will exit on : | ||
| # -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands', | ||
| set -e | ||
| set -u | ||
| set -o pipefail | ||
|
|
||
| train_set="train" | ||
| valid_set="dev" | ||
| test_sets="test dev" | ||
|
|
||
| asr_config=conf/tuning/train_asr_conformer.yaml | ||
| inference_config=conf/decode_asr.yaml | ||
|
|
||
| ./asr.sh \ | ||
| --lang en \ | ||
| --nj 8 \ | ||
| --ngpu 2 \ | ||
| --gpu_inference true \ | ||
| --inference_nj 2 \ | ||
| --feats_type raw \ | ||
| --audio_format "flac.ark" \ | ||
| --token_type bpe \ | ||
| --nbpe 500 \ | ||
| --use_lm false \ | ||
| --asr_config "${asr_config}" \ | ||
| --inference_config "${inference_config}" \ | ||
| --train_set "${train_set}" \ | ||
| --valid_set "${valid_set}" \ | ||
| --test_sets "${test_sets}" \ | ||
| --speed_perturb_factors "0.9 1.0 1.1" \ | ||
| --bpe_train_text "data/${train_set}/text" \ | ||
| --lm_train_text "data/${train_set}/text" "$@" |