|
config: conf/tuning/train_asr_conformer5.yaml |
|
print_config: false |
|
log_level: INFO |
|
dry_run: false |
|
iterator_type: sequence |
|
output_dir: exp/asr_train_asr_conformer5_raw_bpe150_sp |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 1 |
|
num_att_plot: 3 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: null |
|
dist_rank: null |
|
local_rank: 0 |
|
dist_master_addr: null |
|
dist_master_port: null |
|
dist_launcher: null |
|
multiprocessing_distributed: false |
|
unused_parameters: false |
|
sharded_ddp: false |
|
cudnn_enabled: true |
|
cudnn_benchmark: false |
|
cudnn_deterministic: false |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 50 |
|
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: 3 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 1 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: true |
|
log_interval: null |
|
use_matplotlib: true |
|
use_tensorboard: true |
|
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: [] |
|
ignore_init_mismatch: false |
|
freeze_param: [] |
|
num_iters_per_epoch: null |
|
batch_size: 20 |
|
valid_batch_size: null |
|
batch_bins: 2500000 |
|
valid_batch_bins: null |
|
train_shape_file: |
|
- exp/asr_stats_raw_bpe150_sp/train/speech_shape |
|
- exp/asr_stats_raw_bpe150_sp/train/text_shape.bpe |
|
valid_shape_file: |
|
- exp/asr_stats_raw_bpe150_sp/valid/speech_shape |
|
- exp/asr_stats_raw_bpe150_sp/valid/text_shape.bpe |
|
batch_type: numel |
|
valid_batch_type: null |
|
fold_length: |
|
- 80000 |
|
- 150 |
|
sort_in_batch: descending |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 500 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/train_sp/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/train_sp/text |
|
- text |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/valid/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/valid/text |
|
- text |
|
- text |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
valid_max_cache_size: null |
|
optim: adam |
|
optim_conf: |
|
lr: 4.0 |
|
scheduler: noamlr |
|
scheduler_conf: |
|
model_size: 256 |
|
warmup_steps: 25000 |
|
token_list: |
|
- <blank> |
|
- <unk> |
|
- ▁ |
|
- s |
|
- i |
|
- o |
|
- e |
|
- a |
|
- n |
|
- u |
|
- t |
|
- r |
|
- ▁c |
|
- ▁a |
|
- é |
|
- c |
|
- l |
|
- ▁de |
|
- ▁d |
|
- d |
|
- ▁est |
|
- m |
|
- ▁le |
|
- p |
|
- er |
|
- v |
|
- f |
|
- ▁l |
|
- ▁s |
|
- à |
|
- ▁m |
|
- ▁la |
|
- ▁p |
|
- re |
|
- ▁un |
|
- ▁il |
|
- ▁vous |
|
- nt |
|
- g |
|
- te |
|
- ur |
|
- in |
|
- ▁qu |
|
- il |
|
- ce |
|
- ▁en |
|
- ▁je |
|
- tre |
|
- et |
|
- ez |
|
- h |
|
- le |
|
- ▁pas |
|
- ▁b |
|
- or |
|
- ve |
|
- b |
|
- x |
|
- ▁une |
|
- ▁y |
|
- ▁au |
|
- ▁bien |
|
- ▁vo |
|
- ge |
|
- ir |
|
- ▁t |
|
- ▁on |
|
- ▁oui |
|
- ▁j |
|
- ▁n |
|
- ment |
|
- ▁ma |
|
- ▁tr |
|
- ▁re |
|
- que |
|
- ▁dan |
|
- ▁par |
|
- ▁du |
|
- ▁que |
|
- è |
|
- ont |
|
- ▁ici |
|
- ▁euh |
|
- ▁se |
|
- ▁ne |
|
- ▁pour |
|
- aire |
|
- z |
|
- ▁ave |
|
- j |
|
- ▁nous |
|
- ▁bon |
|
- ▁tout |
|
- ▁mais |
|
- ▁monsieur |
|
- ette |
|
- ▁tou |
|
- ement |
|
- ▁va |
|
- ▁sur |
|
- ê |
|
- ▁médecin |
|
- tion |
|
- rès |
|
- elle |
|
- ▁alors |
|
- ▁sui |
|
- y |
|
- ▁voir |
|
- ▁ou |
|
- ▁allez |
|
- ▁che |
|
- ▁eau |
|
- and |
|
- ait |
|
- ▁comme |
|
- ▁manivelle |
|
- ▁plaît |
|
- ▁cric |
|
- vous |
|
- ▁bonjour |
|
- puis |
|
- ▁peut |
|
- ▁plus |
|
- ▁malade |
|
- ommes |
|
- ▁route |
|
- ▁deux |
|
- ▁alle |
|
- ▁fait |
|
- droit |
|
- ▁aussi |
|
- vien |
|
- ▁hui |
|
- ▁pharmacie |
|
- ▁merci |
|
- ▁heure |
|
- ▁gauche |
|
- ▁camarade |
|
- û |
|
- ô |
|
- w |
|
- œ |
|
- k |
|
- ù |
|
- â |
|
- î |
|
- ç |
|
- q |
|
- <sos/eos> |
|
init: null |
|
input_size: null |
|
ctc_conf: |
|
dropout_rate: 0.0 |
|
ctc_type: builtin |
|
reduce: true |
|
ignore_nan_grad: true |
|
joint_net_conf: null |
|
model_conf: |
|
ctc_weight: 0.3 |
|
lsm_weight: 0.1 |
|
length_normalized_loss: false |
|
use_preprocessor: true |
|
token_type: bpe |
|
bpemodel: data/token_list/bpe_unigram150/bpe.model |
|
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' |
|
frontend: default |
|
frontend_conf: |
|
n_fft: 512 |
|
win_length: 400 |
|
hop_length: 160 |
|
fs: 16k |
|
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: global_mvn |
|
normalize_conf: |
|
stats_file: exp/asr_stats_raw_bpe150_sp/train/feats_stats.npz |
|
preencoder: null |
|
preencoder_conf: {} |
|
encoder: conformer |
|
encoder_conf: |
|
input_layer: conv2d |
|
num_blocks: 12 |
|
linear_units: 2048 |
|
dropout_rate: 0.1 |
|
output_size: 256 |
|
attention_heads: 4 |
|
attention_dropout_rate: 0.0 |
|
pos_enc_layer_type: rel_pos |
|
selfattention_layer_type: rel_selfattn |
|
activation_type: swish |
|
macaron_style: true |
|
use_cnn_module: true |
|
cnn_module_kernel: 15 |
|
postencoder: null |
|
postencoder_conf: {} |
|
decoder: transformer |
|
decoder_conf: |
|
input_layer: embed |
|
num_blocks: 6 |
|
linear_units: 2048 |
|
dropout_rate: 0.1 |
|
required: |
|
- output_dir |
|
- token_list |
|
version: 0.10.7a1 |
|
distributed: false |
|
|