config: conf/train_asr_hubert.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/asr_hubert_pt
ngpu: 1
seed: 0
num_workers: 1
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: null
dist_launcher: null
multiprocessing_distributed: true
unused_parameters: true
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 20
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: 2
no_forward_run: false
resume: true
train_dtype: float32
use_amp: false
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: true
freeze_param: []
num_iters_per_epoch: 10000
batch_size: 20
valid_batch_size: null
batch_bins: 9000000
valid_batch_bins: null
train_shape_file:
- exp/asr_stats_raw_char_sp/train/speech_shape
- exp/asr_stats_raw_char_sp/train/text_shape.char
valid_shape_file:
- exp/asr_stats_raw_char_sp/valid/speech_shape
- exp/asr_stats_raw_char_sp/valid/text_shape.char
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/cheat_sp/wav.scp
    - speech
    - sound
-   - dump/raw/cheat_sp/text
    - text
    - text
valid_data_path_and_name_and_type:
-   - dump/raw/test/wav.scp
    - speech
    - sound
-   - dump/raw/test/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: 0.0005
    weight_decay: 1.0e-06
scheduler: warmuplr
scheduler_conf:
    warmup_steps: 5000
token_list:
- <blank>
- <unk>
- <space>
- า
- น
- ่
- อ
- ร
- ้
- ง
- ก
- เ
- ม
- ย
- ั
- ล
- ว
- ี
- ห
- ด
- บ
- ส
- ะ
- ท
- ิ
- ค
- ต
- ป
- ข
- แ
- จ
- ไ
- พ
- ื
- ุ
- ู
- ็
- ใ
- ช
- ์
- ำ
- ึ
- โ
- ผ
- ถ
- ซ
- ณ
- ศ
- ฟ
- ญ
- ธ
- ภ
- ษ
- ฉ
- ๊
- ฝ
- ฮ
- ๋
- ฐ
- ฤ
- ฏ
- ฎ
- ฆ
- ฒ
- ฑ
- ฬ
- ฌ
- ฯ
- <sos/eos>
init: null
input_size: 1
ctc_conf:
    dropout_rate: 0.0
    ctc_type: builtin
    reduce: true
    ignore_nan_grad: 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'
frontend: null
frontend_conf: {}
specaug: null
specaug_conf: {}
normalize: utterance_mvn
normalize_conf: {}
model: espnet
model_conf:
    ctc_weight: 0.3
    lsm_weight: 0.1
    length_normalized_loss: false
preencoder: null
preencoder_conf: {}
encoder: hubert
encoder_conf:
    output_size: 256
    normalize_before: false
    hubert_url: https://dl.fbaipublicfiles.com/hubert/hubert_base_ls960.pt
    hubert_dir_path: ./downloads/hubert_pretrained_models/hubert_base_ls960.pt
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
required:
- output_dir
- token_list
version: 0.10.7a1
distributed: true