config.yml

plbert_params:
    vocab_size: 178
    hidden_size: 768
    num_attention_heads: 12
    intermediate_size: 2048
    max_position_embeddings: 512
    num_hidden_layers: 12
    dropout: 0.1


model_params:
  multispeaker: true
  vocab: "$;:,.!?¡¿—…\"«»“” ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"

  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: 0.0

  # 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]
      
  
  # 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: 0.19988229232390187
      mean: -4.0
      std: 4.0