Hugging Face's logo

kohei0209
/
tfgridnet_urgent25

Model card Files Community
tfgridnet_urgent25
File size: 6,426 Bytes 
c582091
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
 
config: conf/tuning/train_enh_tfgridnet_dm.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: chunk
valid_iterator_type: null
output_dir: exp/enh_train_enh_tfgridnet_dm_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
unused_parameters: false
sharded_ddp: false
use_deepspeed: false
deepspeed_config: null
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true
use_tf32: false
collect_stats: false
write_collected_feats: false
max_epoch: 30
patience: 5
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - valid
    - loss
    - min
keep_nbest_models: 5
nbest_averaging_interval: 0
grad_clip: 1.0
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_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
use_adapter: false
adapter: lora
save_strategy: all
adapter_conf: {}
pretrain_path: null
init_param:
- exp/enh_train_enh_tfgridnet_raw_1stchallenge/21epoch.pth
ignore_init_mismatch: false
freeze_param: []
num_iters_per_epoch: 4000
batch_size: 2
valid_batch_size: 4
batch_bins: 1000000
valid_batch_bins: null
category_sample_size: 10
train_shape_file:
- exp/enh_stats_16k/train/speech_mix_shape
- exp/enh_stats_16k/train/speech_ref1_shape
valid_shape_file:
- exp/enh_stats_16k/valid/speech_mix_shape
- exp/enh_stats_16k/valid/speech_ref1_shape
batch_type: folded
valid_batch_type: null
fold_length:
- 80000
- 80000
sort_in_batch: descending
shuffle_within_batch: false
sort_batch: descending
multiple_iterator: false
chunk_length: 200
chunk_shift_ratio: 0.5
num_cache_chunks: 128
chunk_excluded_key_prefixes: []
chunk_default_fs: 50
chunk_max_abs_length: 144000
chunk_discard_short_samples: true
train_data_path_and_name_and_type:
-   - dump/raw/speech_train_track1/wav.scp
    - speech_mix
    - sound
-   - dump/raw/speech_train_track1/spk1.scp
    - speech_ref1
    - sound
-   - dump/raw/speech_train_track1/utt2category
    - category
    - text
-   - dump/raw/speech_train_track1/utt2fs
    - fs
    - text_int
valid_data_path_and_name_and_type:
-   - dump/raw/validation/wav.scp
    - speech_mix
    - sound
-   - dump/raw/validation/spk1.scp
    - speech_ref1
    - sound
-   - dump/raw/validation/utt2category
    - category
    - text
-   - dump/raw/validation/utt2fs
    - fs
    - text_int
multi_task_dataset: false
allow_variable_data_keys: false
max_cache_size: 0.0
max_cache_fd: 32
allow_multi_rates: true
valid_max_cache_size: null
exclude_weight_decay: false
exclude_weight_decay_conf: {}
optim: adam
optim_conf:
    lr: 0.0001
    eps: 1.0e-08
    weight_decay: 1.0e-05
scheduler: warmupsteplr
scheduler_conf:
    step_size: 1
    gamma: 0.98
    warmup_steps: 4000
init: null
model_conf:
    normalize_variance_per_ch: true
    categories:
    - 1ch_8000Hz
    - 1ch_16000Hz
    - 1ch_22050Hz
    - 1ch_24000Hz
    - 1ch_32000Hz
    - 1ch_44100Hz
    - 1ch_48000Hz
    - 1ch_8000Hz_reverb
    - 1ch_16000Hz_reverb
    - 1ch_22050Hz_reverb
    - 1ch_24000Hz_reverb
    - 1ch_32000Hz_reverb
    - 1ch_44100Hz_reverb
    - 1ch_48000Hz_reverb
criterions:
-   name: mr_l1_tfd
    conf:
        window_sz:
        - 256
        - 512
        - 768
        - 1024
        hop_sz: null
        eps: 1.0e-08
        time_domain_weight: 0.5
        normalize_variance: true
    wrapper: fixed_order
    wrapper_conf:
        weight: 1.0
-   name: si_snr
    conf:
        eps: 1.0e-07
    wrapper: fixed_order
    wrapper_conf:
        weight: 0.0
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
use_reverberant_ref: false
num_spk: 1
num_noise_type: 1
sample_rate: 8000
force_single_channel: false
channel_reordering: false
categories: []
speech_segment: null
avoid_allzero_segment: true
flexible_numspk: false
dynamic_mixing: false
utt2spk: null
dynamic_mixing_gain_db: 0.0
encoder: stft
encoder_conf:
    n_fft: 256
    hop_length: 128
    use_builtin_complex: true
    default_fs: 8000
separator: tfgridnetv3
separator_conf:
    n_srcs: 1
    n_imics: 1
    n_layers: 6
    lstm_hidden_units: 200
    attn_n_head: 4
    attn_qk_output_channel: 2
    emb_dim: 48
    emb_ks: 4
    emb_hs: 1
    activation: prelu
    eps: 1.0e-05
decoder: stft
decoder_conf:
    n_fft: 256
    hop_length: 128
    default_fs: 8000
mask_module: multi_mask
mask_module_conf: {}
preprocessor: enh
preprocessor_conf:
    speech_volume_normalize: 0.5_1.0
    rir_scp: dump/raw/rir_train.scp
    rir_apply_prob: 0.5
    noise_scp: dump/raw/noise_train.scp
    noise_apply_prob: 1.0
    noise_db_range: '-5_15'
    force_single_channel: true
    channel_reordering: true
    categories:
    - 1ch_8000Hz
    - 1ch_16000Hz
    - 1ch_22050Hz
    - 1ch_24000Hz
    - 1ch_32000Hz
    - 1ch_44100Hz
    - 1ch_48000Hz
    - 1ch_8000Hz_reverb
    - 1ch_16000Hz_reverb
    - 1ch_22050Hz_reverb
    - 1ch_24000Hz_reverb
    - 1ch_32000Hz_reverb
    - 1ch_44100Hz_reverb
    - 1ch_48000Hz_reverb
    data_aug_effects:
    -   - 1.0
        - bandwidth_limitation
        -   res_type: random
    -   - 1.0
        - clipping
        -   min_quantile: 0.1
            max_quantile: 0.9
    -   - 1.0
        -   -   - 0.5
                - codec
                -   format: mp3
                    encoder: null
                    qscale:
                    - 1
                    - 10
            -   - 0.5
                - codec
                -   format: ogg
                    encoder:
                    - vorbis
                    - opus
                    qscale:
                    - -1
                    - 10
    -   - 1.0
        - packet_loss
        -   packet_duration_ms: 20
            packet_loss_rate:
            - 0.05
            - 0.25
            max_continuous_packet_loss: 10
    data_aug_num:
    - 1
    - 3
    data_aug_prob: 0.75
diffusion_model: null
diffusion_model_conf: {}
required:
- output_dir
version: '202409'
distributed: false