ASR_config: Utils/ASR/config.yml
ASR_path: Utils/ASR/epoch_00080.pth
F0_path: Utils/JDC/bst.t7
PLBERT_dir: Utils/PLBERT/
model_params:
  decoder:
    resblock_dilation_sizes:
    - - 1
      - 3
      - 5
    - - 1
      - 3
      - 5
    - - 1
      - 3
      - 5
    resblock_kernel_sizes:
    - 3
    - 7
    - 11
    type: hifigan
    upsample_initial_channel: 512
    upsample_kernel_sizes:
    - 20
    - 10
    - 6
    - 4
    upsample_rates:
    - 10
    - 5
    - 3
    - 2
  diffusion:
    dist:
      estimate_sigma_data: true
      mean: -3.0
      sigma_data: 0.2
      std: 1.0
    embedding_mask_proba: 0.1
    transformer:
      head_features: 64
      multiplier: 2
      num_heads: 8
      num_layers: 3
  dim_in: 64
  dropout: 0.2
  hidden_dim: 512
  max_conv_dim: 512
  max_dur: 50
  multispeaker: false
  n_layer: 3
  n_mels: 80
  n_token: 178
  slm:
    hidden: 768
    initial_channel: 64
    model: microsoft/wavlm-base-plus
    nlayers: 13
    sr: 16000
  style_dim: 128
preprocess_params:
  spect_params:
    hop_length: 300
    n_fft: 2048
    win_length: 1200
  sr: 24000