File size: 2,801 Bytes
ef80619 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
config: conf/tuning/train_enh_rnn_tf.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/enh_train_enh_rnn_tf_raw
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
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 100
patience: 10
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
- - valid
- si_snr
- max
- - valid
- loss
- min
keep_nbest_models: 1
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
unused_parameters: false
use_tensorboard: true
use_wandb: false
wandb_project: null
wandb_id: null
pretrain_path: null
init_param: []
freeze_param: []
num_iters_per_epoch: null
batch_size: 8
valid_batch_size: null
batch_bins: 1000000
valid_batch_bins: null
train_shape_file:
- exp/enh_stats_8k/train/speech_mix_shape
- exp/enh_stats_8k/train/speech_ref1_shape
- exp/enh_stats_8k/train/speech_ref2_shape
valid_shape_file:
- exp/enh_stats_8k/valid/speech_mix_shape
- exp/enh_stats_8k/valid/speech_ref1_shape
- exp/enh_stats_8k/valid/speech_ref2_shape
batch_type: folded
valid_batch_type: null
fold_length:
- 80000
- 80000
- 80000
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/tr_min_8k/wav.scp
- speech_mix
- sound
- - dump/raw/tr_min_8k/spk1.scp
- speech_ref1
- sound
- - dump/raw/tr_min_8k/spk2.scp
- speech_ref2
- sound
valid_data_path_and_name_and_type:
- - dump/raw/cv_min_8k/wav.scp
- speech_mix
- sound
- - dump/raw/cv_min_8k/spk1.scp
- speech_ref1
- sound
- - dump/raw/cv_min_8k/spk2.scp
- speech_ref2
- sound
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
valid_max_cache_size: null
optim: adam
optim_conf:
lr: 0.001
eps: 1.0e-08
weight_decay: 1.0e-07
scheduler: reducelronplateau
scheduler_conf:
mode: min
factor: 0.7
patience: 1
init: xavier_uniform
model_conf:
loss_type: mask_mse
mask_type: psm
use_preprocessor: false
encoder: stft
encoder_conf:
n_fft: 256
hop_length: 128
separator: rnn
separator_conf:
rnn_type: blstm
num_spk: 2
nonlinear: relu
layer: 3
unit: 896
dropout: 0.5
decoder: stft
decoder_conf:
n_fft: 256
hop_length: 128
required:
- output_dir
version: 0.9.7
distributed: false
|