|
config: conf/tuning/train_sot_asr_conformer.yaml |
|
print_config: false |
|
log_level: INFO |
|
drop_last_iter: false |
|
dry_run: false |
|
iterator_type: sequence |
|
valid_iterator_type: null |
|
output_dir: exp/asr_train_sot_asr_conformer_raw_en_char_sp_finetune_ls100_45epoch_new_whamr_only |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 16 |
|
num_att_plot: 3 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: 2 |
|
dist_rank: 0 |
|
local_rank: 0 |
|
dist_master_addr: localhost |
|
dist_master_port: 54011 |
|
dist_launcher: null |
|
multiprocessing_distributed: true |
|
unused_parameters: false |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: true |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 60 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- acc |
|
- max |
|
keep_nbest_models: 10 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 5.0 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 4 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: false |
|
log_interval: null |
|
use_matplotlib: true |
|
use_tensorboard: true |
|
create_graph_in_tensorboard: false |
|
use_wandb: false |
|
wandb_project: null |
|
wandb_id: null |
|
wandb_entity: null |
|
wandb_name: null |
|
wandb_model_log_interval: -1 |
|
detect_anomaly: false |
|
pretrain_path: null |
|
init_param: |
|
- /star-home/jinzengrui/dev/espnet/egs2/librimix/sot_asr1_pretrain/exp/asr_train_sot_asr_conformer_raw_en_char_sp/45epoch.pth |
|
ignore_init_mismatch: false |
|
freeze_param: [] |
|
num_iters_per_epoch: null |
|
batch_size: 20 |
|
valid_batch_size: null |
|
batch_bins: 10000000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/asr_stats_raw_en_char/train/speech_shape |
|
- exp/asr_stats_raw_en_char/train/text_shape.char |
|
valid_shape_file: |
|
- exp/asr_stats_raw_en_char/valid/speech_shape |
|
- exp/asr_stats_raw_en_char/valid/text_shape.char |
|
batch_type: numel |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 150 |
|
sort_in_batch: descending |
|
shuffle_within_batch: false |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 500 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
chunk_excluded_key_prefixes: [] |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/tr_mix_clean_reverb_max_16k_sp/wav.scp |
|
- speech |
|
- kaldi_ark |
|
- - dump/raw/tr_mix_clean_reverb_max_16k_sp/text |
|
- text |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/cv_mix_clean_reverb_max_16k/wav.scp |
|
- speech |
|
- kaldi_ark |
|
- - dump/raw/cv_mix_clean_reverb_max_16k/text |
|
- text |
|
- text |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
valid_max_cache_size: null |
|
exclude_weight_decay: false |
|
exclude_weight_decay_conf: {} |
|
optim: adam |
|
optim_conf: |
|
lr: 0.002 |
|
weight_decay: 1.0e-06 |
|
scheduler: warmuplr |
|
scheduler_conf: |
|
warmup_steps: 20000 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- <sc> |
|
- <space> |
|
- E |
|
- T |
|
- A |
|
- O |
|
- N |
|
- I |
|
- H |
|
- S |
|
- R |
|
- D |
|
- L |
|
- U |
|
- M |
|
- C |
|
- W |
|
- F |
|
- G |
|
- Y |
|
- P |
|
- B |
|
- V |
|
- K |
|
- '''' |
|
- X |
|
- J |
|
- Q |
|
- Z |
|
- <sos/eos> |
|
init: null |
|
input_size: null |
|
ctc_conf: |
|
dropout_rate: 0.0 |
|
ctc_type: builtin |
|
reduce: true |
|
ignore_nan_grad: null |
|
zero_infinity: true |
|
joint_net_conf: null |
|
use_preprocessor: true |
|
token_type: char |
|
bpemodel: null |
|
non_linguistic_symbols: null |
|
cleaner: null |
|
g2p: null |
|
speech_volume_normalize: null |
|
rir_scp: null |
|
rir_apply_prob: 1.0 |
|
noise_scp: null |
|
noise_apply_prob: 1.0 |
|
noise_db_range: '13_15' |
|
short_noise_thres: 0.5 |
|
aux_ctc_tasks: [] |
|
frontend: default |
|
frontend_conf: |
|
fs: 16k |
|
specaug: null |
|
specaug_conf: {} |
|
normalize: global_mvn |
|
normalize_conf: |
|
stats_file: exp/asr_stats_raw_en_char/train/feats_stats.npz |
|
model: espnet |
|
model_conf: |
|
ctc_weight: 0.0 |
|
lsm_weight: 0.1 |
|
length_normalized_loss: false |
|
preencoder: null |
|
preencoder_conf: {} |
|
encoder: conformer |
|
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: 0.1 |
|
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 |
|
postencoder: null |
|
postencoder_conf: {} |
|
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 |
|
preprocessor: multi |
|
preprocessor_conf: |
|
speaker_change_symbol: |
|
- <sc> |
|
required: |
|
- output_dir |
|
- token_list |
|
version: '202308' |
|
distributed: true |
|
|