config.yml

log_dir: "/style_tts2/Models/FineTune.AudioBook"
log_interval: 10
device: "cuda"
epochs: 25 # number of finetuning epoch
batch_size: 6
max_len: 300 # maximum number of frames
pretrained_model_repo: "yl4579/StyleTTS2-LibriTTS"
pretrained_model_filename: "Models/LibriTTS/epochs_2nd_00020.pth"
second_stage_load_pretrained: true # set to true if the pre-trained model is for 2nd stage
load_only_params: true # set to true if do not want to load epoch numbers and optimizer parameters

F0_path: "/root/Utils/JDC/bst.t7"
ASR_config: "/root/Utils/ASR/config.yml"
ASR_path: "/root/Utils/ASR/epoch_00080.pth"
PLBERT_repo_id: "fadi77/pl-bert"
PLBERT_dirname: "models/mlm_only_with_diacritics"

data_params:
  train_data: "Data/youtube_train_list.txt"
  val_data: "Data/youtube_val_list.txt"
  root_path: "Youtube/wavs"
  OOD_data: "Data/youtube_train_list.txt"
  min_length: 50 # sample until texts with this size are obtained for OOD texts

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 # number of phoneme tokens
  max_dur: 50 # maximum duration of a single phoneme
  style_dim: 128 # style vector size
  
  dropout: 0.2

  # config for decoder
  decoder: 
      type: 'hifigan' # either hifigan or istftnet
      resblock_kernel_sizes: [3,7,11]
      upsample_rates :  [10,5,3,2]
      upsample_initial_channel: 512
      resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]]
      upsample_kernel_sizes: [20,10,6,4]
      
  # speech language model config
  slm:
      model: 'microsoft/wavlm-base-plus'
      sr: 16000 # sampling rate of SLM
      hidden: 768 # hidden size of SLM
      nlayers: 13 # number of layers of SLM
      initial_channel: 64 # initial channels of SLM discriminator head
  
  # style diffusion model config
  diffusion:
    embedding_mask_proba: 0.1
    # transformer config
    transformer:
      num_layers: 3
      num_heads: 8
      head_features: 64
      multiplier: 2

    # diffusion distribution config
    dist:
      sigma_data: 0.2 # placeholder for estimate_sigma_data set to false
      estimate_sigma_data: true # estimate sigma_data from the current batch if set to true
      mean: -3.0
      std: 1.0
  
loss_params:
    lambda_mel: 5. # mel reconstruction loss
    lambda_gen: 1. # generator loss
    lambda_slm: 1. # slm feature matching loss
    
    lambda_mono: 1. # monotonic alignment loss (TMA)
    lambda_s2s: 1. # sequence-to-sequence loss (TMA)

    lambda_F0: 1. # F0 reconstruction loss
    lambda_norm: 1. # norm reconstruction loss
    lambda_dur: 1. # duration loss
    lambda_ce: 20. # duration predictor probability output CE loss
    lambda_sty: 1. # style reconstruction loss
    lambda_diff: 1. # score matching loss

    # Note: Current values for training are only adequate for second stage finetuning.
    diffusion_training_epoch: 5
    joint_training_epoch: 100

# Note: Current values for learnings rates are very low. This is only adequate for second stage finetuning.
optimizer_params:
  lr: 0.0001 # general learning rate
  bert_lr: 0.00001 # learning rate for PLBERT
  ft_lr: 0.0001 # learning rate for acoustic modules
  
slmadv_params:
  min_len: 400 # minimum length of samples
  max_len: 500 # maximum length of samples
  batch_percentage: 0.5 # to prevent out of memory, only use half of the original batch size
  skip_update: 10 # update the discriminator every this iterations of generator update
  thresh: 5 # gradient norm above which the gradient is scaled
  scale: 0.01 # gradient scaling factor for predictors from SLM discriminators
  sig: 1.5 # sigma for differentiable duration modeling