Hugging Face's logo

espnet
/
anogkongda-librimix_enh_train_raw_valid.si_snr.ave

Audio-to-Audio
ESPnet
English
audio
audio-source-separation
Model card Files Community
anogkongda-librimix_enh_train_raw_valid.si_snr.ave
File size: 2,998 Bytes 
e6abfcf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
144
145
146
147
148
149
150
151
152
153
154
155
 
config: ./conf/train.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: chunk
output_dir: exp/enh_train_raw
ngpu: 1
seed: 0
num_workers: 4
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: 4
dist_rank: 0
local_rank: 0
dist_master_addr: localhost
dist_master_port: 48369
dist_launcher: null
multiprocessing_distributed: true
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
collect_stats: false
write_collected_feats: false
max_epoch: 200
patience: 5
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: 16
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
- exp/enh_stats_8k/train/noise_ref1_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
- exp/enh_stats_8k/valid/noise_ref1_shape
batch_type: folded
valid_batch_type: null
fold_length:
- 80000
- 80000
- 80000
- 80000
sort_in_batch: descending
sort_batch: descending
multiple_iterator: false
chunk_length: 24000
chunk_shift_ratio: 0.5
num_cache_chunks: 1024
train_data_path_and_name_and_type:
-   - dump/raw/train/wav.scp
    - speech_mix
    - sound
-   - dump/raw/train/spk1.scp
    - speech_ref1
    - sound
-   - dump/raw/train/spk2.scp
    - speech_ref2
    - sound
-   - dump/raw/train/noise1.scp
    - noise_ref1
    - sound
valid_data_path_and_name_and_type:
-   - dump/raw/dev/wav.scp
    - speech_mix
    - sound
-   - dump/raw/dev/spk1.scp
    - speech_ref1
    - sound
-   - dump/raw/dev/spk2.scp
    - speech_ref2
    - sound
-   - dump/raw/dev/noise1.scp
    - noise_ref1
    - 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
    weight_decay: 0
scheduler: reducelronplateau
scheduler_conf:
    mode: min
    factor: 0.5
    patience: 1
init: xavier_uniform
model_conf:
    loss_type: si_snr
use_preprocessor: false
encoder: conv
encoder_conf:
    channel: 512
    kernel_size: 16
    stride: 8
separator: tcn
separator_conf:
    num_spk: 2
    layer: 8
    stack: 3
    bottleneck_dim: 128
    hidden_dim: 512
    kernel: 3
    causal: false
    norm_type: gLN
    nonlinear: relu
decoder: conv
decoder_conf:
    channel: 512
    kernel_size: 16
    stride: 8
required:
- output_dir
version: 0.9.7
distributed: true