Hugging Face's logo

Fhrozen
/
vctk_hifigan.full_band.v1

Audio-to-Audio
ESPnet
English
audio
vocoder
Model card Files Community
vctk_hifigan.full_band.v1
File size: 3,551 Bytes 
5731db4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
allow_cache: true
batch_max_steps: 8400
batch_size: 16
config: conf/hifigan.full_band.v1.yaml
dev_dumpdir: dump/dev_all/norm
dev_feats_scp: null
dev_segments: null
dev_wav_scp: null
discriminator_adv_loss_params:
  average_by_discriminators: false
discriminator_grad_norm: -1
discriminator_optimizer_params:
  betas:
  - 0.5
  - 0.9
  lr: 0.0002
  weight_decay: 0.0
discriminator_optimizer_type: Adam
discriminator_params:
  follow_official_norm: true
  period_discriminator_params:
    bias: true
    channels: 32
    downsample_scales:
    - 3
    - 3
    - 3
    - 3
    - 1
    in_channels: 1
    kernel_sizes:
    - 5
    - 3
    max_downsample_channels: 1024
    nonlinear_activation: LeakyReLU
    nonlinear_activation_params:
      negative_slope: 0.1
    out_channels: 1
    use_spectral_norm: false
    use_weight_norm: true
  periods:
  - 2
  - 3
  - 5
  - 7
  - 11
  scale_discriminator_params:
    bias: true
    channels: 128
    downsample_scales:
    - 4
    - 4
    - 4
    - 4
    - 1
    in_channels: 1
    kernel_sizes:
    - 15
    - 41
    - 5
    - 3
    max_downsample_channels: 1024
    max_groups: 16
    nonlinear_activation: LeakyReLU
    nonlinear_activation_params:
      negative_slope: 0.1
    out_channels: 1
  scale_downsample_pooling: AvgPool1d
  scale_downsample_pooling_params:
    kernel_size: 4
    padding: 2
    stride: 2
  scales: 3
discriminator_scheduler_params:
  gamma: 0.5
  milestones:
  - 200000
  - 400000
  - 600000
  - 800000
discriminator_scheduler_type: MultiStepLR
discriminator_train_start_steps: 0
discriminator_type: HiFiGANMultiScaleMultiPeriodDiscriminator
distributed: false
eval_interval_steps: 1000
feat_match_loss_params:
  average_by_discriminators: false
  average_by_layers: false
  include_final_outputs: false
fft_size: 2048
fmax: 22050
fmin: 0
format: hdf5
generator_adv_loss_params:
  average_by_discriminators: false
generator_grad_norm: -1
generator_optimizer_params:
  betas:
  - 0.5
  - 0.9
  lr: 0.0002
  weight_decay: 0.0
generator_optimizer_type: Adam
generator_params:
  bias: true
  channels: 512
  in_channels: 80
  kernel_size: 7
  nonlinear_activation: LeakyReLU
  nonlinear_activation_params:
    negative_slope: 0.1
  out_channels: 1
  resblock_dilations:
  - - 1
    - 3
    - 5
  - - 1
    - 3
    - 5
  - - 1
    - 3
    - 5
  resblock_kernel_sizes:
  - 3
  - 7
  - 11
  upsample_kernel_sizes:
  - 10
  - 10
  - 8
  - 6
  upsample_scales:
  - 5
  - 5
  - 4
  - 3
  use_additional_convs: true
  use_weight_norm: true
generator_scheduler_params:
  gamma: 0.5
  milestones:
  - 200000
  - 400000
  - 600000
  - 800000
generator_scheduler_type: MultiStepLR
generator_train_start_steps: 1
generator_type: HiFiGANGenerator
global_gain_scale: 1.0
hop_size: 300
lambda_adv: 1.0
lambda_aux: 45.0
lambda_feat_match: 2.0
log_interval_steps: 100
mel_loss_params:
  fft_size: 2048
  fmax: 22050
  fmin: 0
  fs: 44100
  hop_size: 300
  log_base: null
  num_mels: 80
  win_length: 1200
  window: hann
num_mels: 80
num_save_intermediate_results: 4
num_workers: 6
outdir: exp/train_nodev_all_vctk_hifigan.full_band.v1
pin_memory: true
pretrain: ''
rank: 0
remove_short_samples: false
resume: ''
sampling_rate: 44100
save_interval_steps: 10000
train_dumpdir: dump/train_nodev_all/norm
train_feats_scp: null
train_max_steps: 2500000
train_segments: null
train_wav_scp: null
trim_frame_size: 1024
trim_hop_size: 256
trim_silence: false
trim_threshold_in_db: 20
use_feat_match_loss: true
use_mel_loss: true
use_stft_loss: false
verbose: 1
version: 0.5.5
win_length: 1200
window: hann