PaddleSpeech/examples/canton/tts3/conf/default.yaml

###########################################################
#                FEATURE EXTRACTION SETTING               #
###########################################################

fs: 24000          # sr
n_fft: 2048        # FFT size (samples).
n_shift: 300       # Hop size (samples). 12.5ms
win_length: 1200   # Window length (samples). 50ms
                   # If set to null, it will be the same as fft_size.
window: "hann"     # Window function.

# Only used for feats_type != raw

fmin: 80           # Minimum frequency of Mel basis.
fmax: 7600         # Maximum frequency of Mel basis.
n_mels: 80         # The number of mel basis.

# Only used for the model using pitch features (e.g. FastSpeech2)
# The canton datasets we use are different from others like Databaker or LJSpeech, 
# we set it to 110 to avoid too many zero-pitch problem. 
# Reference: https://github.com/JeremyCCHsu/Python-Wrapper-for-World-Vocoder/issues/38
f0min: 110          # Minimum f0 for pitch extraction.
f0max: 400         # Maximum f0 for pitch extraction.


###########################################################
#                       DATA SETTING                      #
###########################################################
batch_size: 32
num_workers: 2


###########################################################
#                       MODEL SETTING                     #
###########################################################
model:
    adim: 384         # attention dimension
    aheads: 2         # number of attention heads
    elayers: 4        # number of encoder layers
    eunits: 1536      # number of encoder ff units
    dlayers: 4        # number of decoder layers
    dunits: 1536      # number of decoder ff units
    positionwise_layer_type: conv1d   # type of position-wise layer
    positionwise_conv_kernel_size: 3  # kernel size of position wise conv layer
    duration_predictor_layers: 2      # number of layers of duration predictor
    duration_predictor_chans: 256     # number of channels of duration predictor
    duration_predictor_kernel_size: 3 # filter size of duration predictor
    postnet_layers: 5                 # number of layers of postnset
    postnet_filts: 5                  # filter size of conv layers in postnet
    postnet_chans: 256                # number of channels of conv layers in postnet
    use_scaled_pos_enc: True          # whether to use scaled positional encoding
    encoder_normalize_before: True    # whether to perform layer normalization before the input
    decoder_normalize_before: True    # whether to perform layer normalization before the input
    reduction_factor: 1               # reduction factor
    init_type: xavier_uniform         # initialization type
    init_enc_alpha: 1.0               # initial value of alpha of encoder scaled position encoding
    init_dec_alpha: 1.0               # initial value of alpha of decoder scaled position encoding
    transformer_enc_dropout_rate: 0.2            # dropout rate for transformer encoder layer
    transformer_enc_positional_dropout_rate: 0.2 # dropout rate for transformer encoder positional encoding
    transformer_enc_attn_dropout_rate: 0.2       # dropout rate for transformer encoder attention layer
    transformer_dec_dropout_rate: 0.2            # dropout rate for transformer decoder layer
    transformer_dec_positional_dropout_rate: 0.2 # dropout rate for transformer decoder positional encoding
    transformer_dec_attn_dropout_rate: 0.2       # dropout rate for transformer decoder attention layer
    pitch_predictor_layers: 5                  # number of conv layers in pitch predictor
    pitch_predictor_chans: 256                 # number of channels of conv layers in pitch predictor
    pitch_predictor_kernel_size: 5             # kernel size of conv leyers in pitch predictor
    pitch_predictor_dropout: 0.5               # dropout rate in pitch predictor
    pitch_embed_kernel_size: 1                 # kernel size of conv embedding layer for pitch
    pitch_embed_dropout: 0.0                   # dropout rate after conv embedding layer for pitch
    stop_gradient_from_pitch_predictor: True   # whether to stop the gradient from pitch predictor to encoder
    energy_predictor_layers: 2                 # number of conv layers in energy predictor
    energy_predictor_chans: 256                # number of channels of conv layers in energy predictor
    energy_predictor_kernel_size: 3            # kernel size of conv leyers in energy predictor
    energy_predictor_dropout: 0.5              # dropout rate in energy predictor
    energy_embed_kernel_size: 1                # kernel size of conv embedding layer for energy
    energy_embed_dropout: 0.0                  # dropout rate after conv embedding layer for energy
    stop_gradient_from_energy_predictor: False # whether to stop the gradient from energy predictor to encoder
    spk_embed_dim: 256                         # speaker embedding dimension
    spk_embed_integration_type: concat         # speaker embedding integration type



###########################################################
#                       UPDATER SETTING                   #
###########################################################
updater:
    use_masking: True                 # whether to apply masking for padded part in loss calculation


###########################################################
#                     OPTIMIZER SETTING                   #
###########################################################
optimizer:
    optim: adam               # optimizer type
    learning_rate: 0.001      # learning rate

###########################################################
#                     TRAINING SETTING                    #
###########################################################
max_epoch: 1000
num_snapshots: 5


###########################################################
#                       OTHER SETTING                     #
###########################################################
seed: 10086