File size: 4,361 Bytes
98f685a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
accumulate_grad_batches: 1
adam_b1: 0.8
adam_b2: 0.99
amp: false
audio_num_mel_bins: 80
audio_sample_rate: 24000
aux_context_window: 0
#base_config:
#- egs/egs_bases/singing/pwg.yaml
#- egs/egs_bases/tts/vocoder/hifigan.yaml
binarization_args:
  reset_phone_dict: true
  reset_word_dict: true
  shuffle: false
  trim_eos_bos: false
  trim_sil: false
  with_align: false
  with_f0: true
  with_f0cwt: false
  with_linear: false
  with_spk_embed: false
  with_spk_id: true
  with_txt: false
  with_wav: true
  with_word: false
binarizer_cls: data_gen.tts.singing.binarize.SingingBinarizer
binary_data_dir: data/binary/big_popcs_24k_hop128
check_val_every_n_epoch: 10
clip_grad_norm: 1
clip_grad_value: 0
datasets: []
debug: false
dec_ffn_kernel_size: 9
dec_layers: 4
dict_dir: ''
disc_start_steps: 40000
discriminator_grad_norm: 1
discriminator_optimizer_params:
  eps: 1.0e-06
  lr: 0.0002
  weight_decay: 0.0
discriminator_params:
  bias: true
  conv_channels: 64
  in_channels: 1
  kernel_size: 3
  layers: 10
  nonlinear_activation: LeakyReLU
  nonlinear_activation_params:
    negative_slope: 0.2
  out_channels: 1
  use_weight_norm: true
discriminator_scheduler_params:
  gamma: 0.999
  step_size: 600
dropout: 0.1
ds_workers: 1
enc_ffn_kernel_size: 9
enc_layers: 4
endless_ds: true
ffn_act: gelu
ffn_padding: SAME
fft_size: 512
fmax: 12000
fmin: 30
frames_multiple: 1
gen_dir_name: ''
generator_grad_norm: 10
generator_optimizer_params:
  eps: 1.0e-06
  lr: 0.0002
  weight_decay: 0.0
generator_params:
  aux_channels: 80
  dropout: 0.0
  gate_channels: 128
  in_channels: 1
  kernel_size: 3
  layers: 30
  out_channels: 1
  residual_channels: 64
  skip_channels: 64
  stacks: 3
  upsample_net: ConvInUpsampleNetwork
  upsample_params:
    upsample_scales:
    - 2
    - 4
    - 4
    - 4
  use_nsf: false
  use_pitch_embed: true
  use_weight_norm: true
generator_scheduler_params:
  gamma: 0.999
  step_size: 600
griffin_lim_iters: 60
hidden_size: 256
hop_size: 128
infer: false
lambda_adv: 1.0
lambda_cdisc: 4.0
lambda_energy: 0.0
lambda_f0: 0.0
lambda_mel: 5.0
lambda_mel_adv: 1.0
lambda_ph_dur: 0.0
lambda_sent_dur: 0.0
lambda_uv: 0.0
lambda_word_dur: 0.0
load_ckpt: ''
loud_norm: false
lr: 2.0
max_epochs: 1000
max_frames: 2400
max_input_tokens: 1550
max_samples: 8192
max_sentences: 20
max_tokens: 24000
max_updates: 3000000
max_valid_sentences: 1
max_valid_tokens: 60000
mel_loss: ssim:0.5|l1:0.5
mel_vmax: 1.5
mel_vmin: -6
min_frames: 0
min_level_db: -120
num_ckpt_keep: 3
num_heads: 2
num_mels: 80
num_sanity_val_steps: 5
num_spk: 100
num_test_samples: 0
num_valid_plots: 10
optimizer_adam_beta1: 0.9
optimizer_adam_beta2: 0.98
out_wav_norm: false
pitch_extractor: parselmouth
pitch_type: frame
pre_align_args:
  allow_no_txt: false
  denoise: false
  sox_resample: true
  sox_to_wav: false
  trim_sil: false
  txt_processor: zh
  use_tone: false
pre_align_cls: data_gen.tts.singing.pre_align.SingingPreAlign
predictor_grad: 0.0
print_nan_grads: false
processed_data_dir: ''
profile_infer: false
raw_data_dir: ''
ref_level_db: 20
rename_tmux: true
rerun_gen: true
resblock: '1'
resblock_dilation_sizes:
- - 1
  - 3
  - 5
- - 1
  - 3
  - 5
- - 1
  - 3
  - 5
resblock_kernel_sizes:
- 3
- 7
- 11
resume_from_checkpoint: 0
save_best: true
save_codes: []
save_f0: true
save_gt: true
scheduler: rsqrt
seed: 1234
sort_by_len: true
stft_loss_params:
  fft_sizes:
  - 1024
  - 2048
  - 512
  hop_sizes:
  - 120
  - 240
  - 50
  win_lengths:
  - 600
  - 1200
  - 240
  window: hann_window
task_cls: tasks.vocoder.hifigan.HifiGanTask
tb_log_interval: 100
test_ids: []
test_input_dir: ''
test_num: 50
test_prefixes: []
test_set_name: test
train_set_name: train
train_sets: ''
upsample_initial_channel: 512
upsample_kernel_sizes:
- 16
- 16
- 4
- 4
upsample_rates:
- 8
- 4
- 2
- 2
use_cdisc: false
use_cond_disc: false
use_fm_loss: false
use_gt_dur: true
use_gt_f0: true
use_mel_loss: true
use_ms_stft: false
use_pitch_embed: true
use_ref_enc: true
use_spec_disc: false
use_spk_embed: false
use_spk_id: false
use_split_spk_id: false
val_check_interval: 2000
valid_infer_interval: 10000
valid_monitor_key: val_loss
valid_monitor_mode: min
valid_set_name: valid
vocoder: pwg
vocoder_ckpt: ''
vocoder_denoise_c: 0.0
warmup_updates: 8000
weight_decay: 0
win_length: null
win_size: 512
window: hann
word_size: 3000
work_dir: checkpoints/0109_hifigan_bigpopcs_hop128