-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #5342 from YoshikiMas/hackathon-2023s
Whisper fine-tuning recipes for CHiME-4 and WSJ
- Loading branch information
Showing
5 changed files
with
216 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
75 changes: 75 additions & 0 deletions
75
egs2/chime4/asr1/conf/tuning/train_asr_whisper_full_warmup1500.yaml
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 +1,75 @@ | ||
| normalize: null | ||
|
|
||
| encoder: whisper | ||
| encoder_conf: | ||
| whisper_model: medium | ||
| dropout_rate: 0.0 | ||
| use_specaug: true | ||
| 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 | ||
|
|
||
|
|
||
| decoder: whisper | ||
| decoder_conf: | ||
| whisper_model: medium | ||
| dropout_rate: 0.0 | ||
|
|
||
| model_conf: | ||
| ctc_weight: 0.0 | ||
| lsm_weight: 0.1 | ||
| length_normalized_loss: false | ||
| sym_sos: "<|startoftranscript|>" | ||
| sym_eos: "<|endoftext|>" | ||
| extract_feats_in_collect_stats: false | ||
|
|
||
|
|
||
| frontend: null | ||
| input_size: 1 # to prevent build_model() from complaining | ||
|
|
||
| seed: 2022 | ||
| log_interval: 100 | ||
| num_att_plot: 0 | ||
| num_workers: 4 | ||
| sort_in_batch: descending # how to sort data in making batch | ||
| sort_batch: descending # how to sort created batches | ||
| batch_type: numel | ||
| batch_bins: 8000000 # good for single GPU w/ 40G mem | ||
| batch_size: 16 | ||
| accum_grad: 4 | ||
| max_epoch: 3 | ||
| patience: none | ||
| init: none | ||
| best_model_criterion: | ||
| - - valid | ||
| - acc | ||
| - max | ||
| keep_nbest_models: 3 | ||
|
|
||
| use_amp: true | ||
| cudnn_deterministic: false | ||
| cudnn_benchmark: false | ||
|
|
||
| optim: adamw | ||
| grad_clip: 1.0 | ||
| optim_conf: | ||
| lr: 1.0e-05 | ||
| weight_decay: 0.01 | ||
| betas: | ||
| - 0.9 | ||
| - 0.99 | ||
| eps: 1.0e-06 | ||
| scheduler: warmuplr | ||
| scheduler_conf: | ||
| warmup_steps: 1500 |
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: 1 | ||
| ctc_weight: 0.0 | ||
| lm_weight: 0.0 | ||
| maxlenratio: 0.3 | ||
| minlenratio: 0.0 | ||
| penalty: 0.0 |
74 changes: 74 additions & 0 deletions
74
egs2/wsj/asr1/conf/tuning/train_asr_whisper_full_warmup3000.yaml
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 @@ | ||
| normalize: null | ||
|
|
||
| encoder: whisper | ||
| encoder_conf: | ||
| whisper_model: medium | ||
| dropout_rate: 0.0 | ||
| use_specaug: true | ||
| 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 | ||
|
|
||
|
|
||
| decoder: whisper | ||
| decoder_conf: | ||
| whisper_model: medium | ||
| dropout_rate: 0.0 | ||
|
|
||
| model_conf: | ||
| ctc_weight: 0.0 | ||
| lsm_weight: 0.1 | ||
| length_normalized_loss: false | ||
| sym_sos: "<|startoftranscript|>" | ||
| sym_eos: "<|endoftext|>" | ||
| extract_feats_in_collect_stats: false | ||
|
|
||
|
|
||
| frontend: null | ||
| input_size: 1 # to prevent build_model() from complaining | ||
|
|
||
| seed: 2022 | ||
| log_interval: 100 | ||
| num_att_plot: 0 | ||
| num_workers: 4 | ||
| sort_in_batch: descending # how to sort data in making batch | ||
| sort_batch: descending # how to sort created batches | ||
| batch_type: numel | ||
| batch_bins: 8000000 # good for single GPU w/ 40G mem | ||
| accum_grad: 4 | ||
| max_epoch: 3 | ||
| patience: none | ||
| init: none | ||
| best_model_criterion: | ||
| - - valid | ||
| - acc | ||
| - max | ||
| keep_nbest_models: 3 | ||
|
|
||
| use_amp: true | ||
| cudnn_deterministic: false | ||
| cudnn_benchmark: false | ||
|
|
||
| optim: adamw | ||
| grad_clip: 1.0 | ||
| optim_conf: | ||
| lr: 1.0e-05 | ||
| weight_decay: 0.01 | ||
| betas: | ||
| - 0.9 | ||
| - 0.99 | ||
| eps: 1.0e-06 | ||
| scheduler: warmuplr | ||
| scheduler_conf: | ||
| warmup_steps: 3000 |