hyperparams.yaml

# ################################
# Model: Tacotroon2 for TTS
# Authors: Artem Ploujnikov, Yingzhi Wang 
# ################################

mask_padding: True
n_mel_channels: 80
n_symbols: 148
symbols_embedding_dim: 512
encoder_kernel_size: 5
encoder_n_convolutions: 3
encoder_embedding_dim: 512
attention_rnn_dim: 1024
attention_dim: 128
attention_location_n_filters: 32
attention_location_kernel_size: 31
n_frames_per_step: 1
decoder_rnn_dim: 1024
prenet_dim: 256
max_decoder_steps: 1000
gate_threshold: 0.5
p_attention_dropout: 0.1
p_decoder_dropout: 0.1
postnet_embedding_dim: 512
postnet_kernel_size: 5
postnet_n_convolutions: 5
decoder_no_early_stopping: False

# Model
model: !new:speechbrain.lobes.models.Tacotron2.Tacotron2
  mask_padding: !ref <mask_padding>
  n_mel_channels: !ref <n_mel_channels>
  # symbols
  n_symbols: !ref <n_symbols>
  symbols_embedding_dim: !ref <symbols_embedding_dim>
  # encoder
  encoder_kernel_size: !ref <encoder_kernel_size>
  encoder_n_convolutions: !ref <encoder_n_convolutions>
  encoder_embedding_dim: !ref <encoder_embedding_dim>
  # attention
  attention_rnn_dim: !ref <attention_rnn_dim>
  attention_dim: !ref <attention_dim>
  # attention location
  attention_location_n_filters: !ref <attention_location_n_filters>
  attention_location_kernel_size: !ref <attention_location_kernel_size>
  # decoder
  n_frames_per_step: !ref <n_frames_per_step>
  decoder_rnn_dim: !ref <decoder_rnn_dim>
  prenet_dim: !ref <prenet_dim>
  max_decoder_steps: !ref <max_decoder_steps>
  gate_threshold: !ref <gate_threshold>
  p_attention_dropout: !ref <p_attention_dropout>
  p_decoder_dropout: !ref <p_decoder_dropout>
  # postnet
  postnet_embedding_dim: !ref <postnet_embedding_dim>
  postnet_kernel_size: !ref <postnet_kernel_size>
  postnet_n_convolutions: !ref <postnet_n_convolutions>
  decoder_no_early_stopping: !ref <decoder_no_early_stopping>

# Function that converts the text into a sequence of valid characters.
text_to_sequence: !name:recipes.LJSpeech.TTS.tacotron2.text_to_sequence.text_to_sequence

modules:
    model: !ref <model>

pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
    loadables:
        model: !ref <model>