espnet-slu-snips/config.yaml

config: conf/tuning/train_asr_hubert_conformer.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/asr_train_asr_hubert_conformer_raw_bpe100_init_paramexpexp_hubert_large_ll60k_weighted_perturbasr_train_asr_conformer7_hubert_960hr_large_raw_en_bpe5000_sp26epoch.pth:::decoder.output_layer,decoder.embed.0,ctc.ctc_lo_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: null
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: 500
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - valid
    - acc
    - max
keep_nbest_models: 10
grad_clip: 5.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 1
no_forward_run: false
resume: true
train_dtype: float32
use_amp: false
log_interval: null
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:
- exp/exp_hubert_large_ll60k_weighted_perturb/asr_train_asr_conformer7_hubert_960hr_large_raw_en_bpe5000_sp/26epoch.pth:::decoder.output_layer,decoder.embed.0,ctc.ctc_lo
ignore_init_mismatch: false
freeze_param:
- frontend.upstream
num_iters_per_epoch: null
batch_size: 20
valid_batch_size: null
batch_bins: 1000000
valid_batch_bins: null
train_shape_file:
- exp/asr_stats_raw_bpe100_sp/train/speech_shape
- exp/asr_stats_raw_bpe100_sp/train/text_shape.bpe
valid_shape_file:
- exp/asr_stats_raw_bpe100_sp/valid/speech_shape
- exp/asr_stats_raw_bpe100_sp/valid/text_shape.bpe
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_sp/wav.scp
    - speech
    - sound
-   - dump/raw/train_sp/text
    - text
    - text
valid_data_path_and_name_and_type:
-   - dump/raw/dev/wav.scp
    - speech
    - sound
-   - dump/raw/dev/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: 0.0002
scheduler: warmuplr
scheduler_conf:
    warmup_steps: 2000
token_list:
- <blank>
- <unk>
- DECREASEBRIGHTNESS
- INCREASEBRIGHTNESS
- SETLIGHTBRIGHTNESS
- SETLIGHTCOLOR
- SWITCHLIGHTOFF
- SWITCHLIGHTON
- ▁
- ▁the
- ▁lights
- ▁to
- e
- ▁in
- ▁turn
- i
- s
- l
- d
- t
- ▁please
- o
- ▁room
- ▁light
- ke
- ▁brightness
- ▁i
- ▁off
- a
- ▁be
- ▁on
- m
- ▁ma
- nt
- ▁wa
- r
- ▁change
- u
- ▁set
- re
- ▁you
- y
- ▁can
- ▁li
- g
- ing
- ▁down
- ▁pink
- p
- ▁two
- v
- ▁lighting
- ▁of
- w
- ▁red
- at
- ting
- ▁bedroom
- ▁s
- ▁la
- ▁need
- ▁twenty
- ▁up
- ▁it
- eve
- ▁me
- f
- ou
- ▁green
- ld
- ▁increase
- ▁brighter
- ▁blue
- ▁color
- ▁bright
- ▁toilet
- ▁kitchen
- ▁dim
- ry
- ▁lower
- ▁bathroom
- ▁switch
- all
- ▁twelve
- ▁dark
- ▁basement
- ▁percent
- x
- j
- k
- c
- b
- n
- '0'
- '3'
- q
- z
- '4'
- h
- <sos/eos>
init: null
input_size: null
ctc_conf:
    dropout_rate: 0.0
    ctc_type: builtin
    reduce: true
    ignore_nan_grad: true
model_conf:
    ctc_weight: 0.3
    lsm_weight: 0.1
    length_normalized_loss: false
    extract_feats_in_collect_stats: false
use_preprocessor: true
token_type: bpe
bpemodel: data/token_list/bpe_unigram100/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: s3prl
frontend_conf:
    frontend_conf:
        upstream: hubert_large_ll60k
    download_dir: ./hub
    multilayer_feature: true
    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: utterance_mvn
normalize_conf: {}
preencoder: linear
preencoder_conf:
    input_size: 1024
    output_size: 80
encoder: conformer
encoder_conf:
    output_size: 512
    attention_heads: 8
    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
    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: 8
    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: 0.10.3a3
distributed: false