configs/config_hindi_english.yml

log_dir: "Models/hindi_english_multispeaker_finetuned"
first_stage_path: "first_stage.pth"
save_freq: 1
log_interval: 10
device: "cuda"

epochs_1st: 15
epochs_2nd: 15

batch_size: 2
max_len: 200

pretrained_model: ""
second_stage_load_pretrained: true
load_only_params: true

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: ""
  val_data: ""
  root_path: ""
  OOD_data: ""
  min_length: 50

# Audio preprocessing (24kHz)
preprocess_params:
  sr: 24000
  spect_params:
    n_fft: 2048
    win_length: 1200
    hop_length: 300

# Model architecture
model_params:
  multispeaker: true
  num_speakers: 5

  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: 0.2

  speaker_embed_dim: 256

  decoder:
    type: "hifigan"
    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
    resblock_kernel_sizes: [3, 7, 11]
    upsample_initial_channel: 512
    upsample_rates: [10, 5, 3, 2]
    upsample_kernel_sizes: [20, 10, 6, 4]

  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: 0.19926648961191362
      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
  lambda_F0: 1.0
  lambda_norm: 1.0
  lambda_dur: 1.0
  lambda_ce: 20.0
  lambda_sty: 1.0
  lambda_diff: 1.0
  TMA_epoch: 2
  diff_epoch: 0
  joint_epoch: 0

optimizer_params:
  lr: 0.00005
  bert_lr: 0.000005
  ft_lr: 0.000005

slmadv_params:
  min_len: 400
  max_len: 500
  batch_percentage: 0.5
  iter: 20
  thresh: 5
  scale: 0.01
  sig: 1.5