pyf98 / wsj_e_branchformer

config: conf/tuning/train_asr_e_branchformer_e12_mlp1024_linear1024.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/asr_train_asr_e_branchformer_e12_mlp1024_linear1024_raw_en_char
ngpu: 1
seed: 0
num_workers: 4
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: true
collect_stats: false
write_collected_feats: false
max_epoch: 100
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: true
log_interval: 100
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: []
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: null
batch_size: 128
valid_batch_size: null
batch_bins: 1000000
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: folded
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_si284/wav.scp
    - speech
    - sound
-   - dump/raw/train_si284/text
    - text
    - text
valid_data_path_and_name_and_type:
-   - dump/raw/test_dev93/wav.scp
    - speech
    - sound
-   - dump/raw/test_dev93/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: 0.005
scheduler: warmuplr
scheduler_conf:
    warmup_steps: 30000
token_list:
- <blank>
- <unk>
- <space>
- E
- T
- A
- N
- I
- O
- S
- R
- H
- L
- D
- C
- U
- M
- P
- F
- G
- Y
- W
- B
- V
- K
- .
- X
- ''''
- J
- Q
- Z
- <NOISE>
- ','
- '-'
- '"'
- '*'
- ':'
- (
- )
- '?'
- '!'
- '&'
- ;
- '1'
- '2'
- '0'
- /
- $
- '{'
- '}'
- '8'
- '9'
- '6'
- '3'
- '5'
- '7'
- '4'
- '~'
- '`'
- _
- <*IN*>
- <*MR.*>
- \
- ^
- <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: data/nlsyms.txt
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
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: 0.3
    lsm_weight: 0.1
    length_normalized_loss: false
preencoder: null
preencoder_conf: {}
encoder: e_branchformer
encoder_conf:
    output_size: 256
    attention_heads: 4
    attention_layer_type: rel_selfattn
    pos_enc_layer_type: rel_pos
    rel_pos_type: latest
    cgmlp_linear_units: 1024
    cgmlp_conv_kernel: 31
    use_linear_after_conv: false
    gate_activation: identity
    num_blocks: 12
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.1
    input_layer: conv2d
    layer_drop_rate: 0.0
    linear_units: 1024
    positionwise_layer_type: linear
    use_ffn: true
    macaron_ffn: true
    merge_conv_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: 0.0
    src_attention_dropout_rate: 0.0
preprocessor: default
preprocessor_conf: {}
required:
- output_dir
- token_list
version: '202211'
distributed: false