config_aoede.yml

log_dir: "Models/aoede"
first_stage_path: "first_stage.pth"
save_freq: 2
log_interval: 10
device: "cuda"

epochs_1st: 100
epochs_2nd: 50
batch_size: 4
max_len: 300

pretrained_model: "Models/aoede/epoch_1st_00014.pth"
second_stage_load_pretrained: true
load_only_params: false  # ✅ Needed to resume full training

F0_path: "Utils/JDC/bst.t7"
ASR_config: "Utils/ASR/config.yml"
ASR_path: "Utils/ASR/epoch_00080.pth"
PLBERT_dir: "Utils/PLBERT/"

data_params:
  train_data: "aoede_dataset/metadata.csv"
  val_data: "aoede_dataset/metadata.csv"
  root_path: "aoede_dataset/wavs"
  OOD_data: "Data/OOD_texts.txt"
  min_length: 50

preprocess_params:
  sr: 24000
  spect_params:
    n_fft: 2048
    win_length: 1200
    hop_length: 300

model_params:
  multispeaker: false
  dim_in: 64
  hidden_dim: 512
  max_conv_dim: 512
  n_layer: 3
  n_mels: 80
  n_token: 178
  max_dur: 50
  style_dim: 128
  dropout: 0.1

  decoder:
    type: "istftnet"
    gen_istft_hop_size: 5
    gen_istft_n_fft: 20
    resblock_kernel_sizes: [3, 7, 11]
    upsample_rates: [10, 6]
    upsample_initial_channel: 512
    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
    upsample_kernel_sizes: [20, 12]

  slm:
    model: "microsoft/wavlm-base-plus"
    sr: 16000
    hidden: 768
    nlayers: 13
    initial_channel: 64

  diffusion:
    embedding_mask_proba: 0.1
    transformer:
      num_layers: 3
      num_heads: 8
      head_features: 64
      multiplier: 2
    dist:
      sigma_data: 0.2
      estimate_sigma_data: true
      mean: -3.0
      std: 1.0

loss_params:
  lambda_mel: 5.0
  lambda_gen: 1.0
  lambda_slm: 1.0
  lambda_mono: 1.0
  lambda_s2s: 1.0
  TMA_epoch: 15

  lambda_F0: 1.0
  lambda_norm: 1.0
  lambda_dur: 1.0
  lambda_ce: 20.0
  lambda_sty: 1.0
  lambda_diff: 1.0

  diff_epoch: 10
  joint_epoch: 30

optimizer_params:
  lr: 0.0001
  bert_lr: 0.00001
  ft_lr: 0.00001

slmadv_params:
  min_len: 400
  max_len: 600
  batch_percentage: 0.5
  iter: 10
  thresh: 5
  scale: 0.01
  sig: 1.5