vctk_hifigan_hubert_large_km50_24khz.v1/config.yml

allow_cache: true
batch_max_steps: 10240
batch_size: 32
config: conf/hifigan_hubert_large_km50_24khz.v1.yaml
dev_dumpdir: dump_hu50/dev/raw
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: true
fft_size: null
fmax: null
fmin: null
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
  concat_spk_emb: false
  in_channels: 512
  kernel_size: 7
  nonlinear_activation: LeakyReLU
  nonlinear_activation_params:
    negative_slope: 0.1
  num_embs: 50
  out_channels: 1
  resblock_dilations:
  - - 1
    - 3
    - 5
  - - 1
    - 3
    - 5
  - - 1
    - 3
    - 5
  resblock_kernel_sizes:
  - 3
  - 7
  - 11
  spk_emb_dim: 512
  upsample_kernal_sizes:
  - 24
  - 20
  - 4
  - 4
  upsample_scales:
  - 12
  - 10
  - 2
  - 2
  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: DiscreteSymbolSpkEmbHiFiGANGenerator
global_gain_scale: 1.0
hop_size: 480
lambda_adv: 1.0
lambda_aux: 45.0
lambda_feat_match: 2.0
log_interval_steps: 100
mel_loss_params:
  fft_size: 2048
  fmax: 8000
  fmin: 0
  fs: 24000
  hop_size: 300
  log_base: null
  num_mels: 80
  win_length: null
  window: hann
num_mels: 2
num_save_intermediate_results: 4
num_workers: 2
outdir: exp/tr_no_dev_vctk_hifigan_hubert_large_km50_24khz.v1
pin_memory: true
pretrain: ''
rank: 0
remove_short_samples: false
resume: exp/tr_no_dev_vctk_hifigan_hubert_large_km50_24khz.v1/checkpoint-150000steps.pkl
sampling_rate: 24000
save_interval_steps: 50000
train_dumpdir: dump_hu50/tr_no_dev/raw
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: 0.5.1
win_length: null
window: null