|
|
|
|
# This configuration tested on 4 GPUs (V100) with 32GB GPU
|
|
|
|
|
# memory. It takes around 2 weeks to finish the training
|
|
|
|
|
# but 100k iters model should generate reasonable results.
|
|
|
|
|
###########################################################
|
|
|
|
|
# FEATURE EXTRACTION SETTING #
|
|
|
|
|
###########################################################
|
|
|
|
|
|
|
|
|
|
fs: 22050 # sr
|
|
|
|
|
n_fft: 1024 # FFT size (samples).
|
|
|
|
|
n_shift: 256 # Hop size (samples). 12.5ms
|
|
|
|
|
win_length: null # Window length (samples). 50ms
|
|
|
|
|
# If set to null, it will be the same as fft_size.
|
|
|
|
|
window: "hann" # Window function.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
##########################################################
|
|
|
|
|
# TTS MODEL SETTING #
|
|
|
|
|
##########################################################
|
|
|
|
|
model:
|
|
|
|
|
# generator related
|
|
|
|
|
generator_type: vits_generator
|
|
|
|
|
generator_params:
|
|
|
|
|
hidden_channels: 192
|
|
|
|
|
spks: -1
|
|
|
|
|
global_channels: -1
|
|
|
|
|
segment_size: 32
|
|
|
|
|
text_encoder_attention_heads: 2
|
|
|
|
|
text_encoder_ffn_expand: 4
|
|
|
|
|
text_encoder_blocks: 6
|
|
|
|
|
text_encoder_positionwise_layer_type: "conv1d"
|
|
|
|
|
text_encoder_positionwise_conv_kernel_size: 3
|
|
|
|
|
text_encoder_positional_encoding_layer_type: "rel_pos"
|
|
|
|
|
text_encoder_self_attention_layer_type: "rel_selfattn"
|
|
|
|
|
text_encoder_activation_type: "swish"
|
|
|
|
|
text_encoder_normalize_before: True
|
|
|
|
|
text_encoder_dropout_rate: 0.1
|
|
|
|
|
text_encoder_positional_dropout_rate: 0.0
|
|
|
|
|
text_encoder_attention_dropout_rate: 0.1
|
|
|
|
|
use_macaron_style_in_text_encoder: True
|
|
|
|
|
use_conformer_conv_in_text_encoder: False
|
|
|
|
|
text_encoder_conformer_kernel_size: -1
|
|
|
|
|
decoder_kernel_size: 7
|
|
|
|
|
decoder_channels: 512
|
|
|
|
|
decoder_upsample_scales: [8, 8, 2, 2]
|
|
|
|
|
decoder_upsample_kernel_sizes: [16, 16, 4, 4]
|
|
|
|
|
decoder_resblock_kernel_sizes: [3, 7, 11]
|
|
|
|
|
decoder_resblock_dilations: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
|
|
|
|
|
use_weight_norm_in_decoder: True
|
|
|
|
|
posterior_encoder_kernel_size: 5
|
|
|
|
|
posterior_encoder_layers: 16
|
|
|
|
|
posterior_encoder_stacks: 1
|
|
|
|
|
posterior_encoder_base_dilation: 1
|
|
|
|
|
posterior_encoder_dropout_rate: 0.0
|
|
|
|
|
use_weight_norm_in_posterior_encoder: True
|
|
|
|
|
flow_flows: 4
|
|
|
|
|
flow_kernel_size: 5
|
|
|
|
|
flow_base_dilation: 1
|
|
|
|
|
flow_layers: 4
|
|
|
|
|
flow_dropout_rate: 0.0
|
|
|
|
|
use_weight_norm_in_flow: True
|
|
|
|
|
use_only_mean_in_flow: True
|
|
|
|
|
stochastic_duration_predictor_kernel_size: 3
|
|
|
|
|
stochastic_duration_predictor_dropout_rate: 0.5
|
|
|
|
|
stochastic_duration_predictor_flows: 4
|
|
|
|
|
stochastic_duration_predictor_dds_conv_layers: 3
|
|
|
|
|
# discriminator related
|
|
|
|
|
discriminator_type: hifigan_multi_scale_multi_period_discriminator
|
|
|
|
|
discriminator_params:
|
|
|
|
|
scales: 1
|
|
|
|
|
scale_downsample_pooling: "AvgPool1D"
|
|
|
|
|
scale_downsample_pooling_params:
|
|
|
|
|
kernel_size: 4
|
|
|
|
|
stride: 2
|
|
|
|
|
padding: 2
|
|
|
|
|
scale_discriminator_params:
|
|
|
|
|
in_channels: 1
|
|
|
|
|
out_channels: 1
|
|
|
|
|
kernel_sizes: [15, 41, 5, 3]
|
|
|
|
|
channels: 128
|
|
|
|
|
max_downsample_channels: 1024
|
|
|
|
|
max_groups: 16
|
|
|
|
|
bias: True
|
|
|
|
|
downsample_scales: [2, 2, 4, 4, 1]
|
|
|
|
|
nonlinear_activation: "leakyrelu"
|
|
|
|
|
nonlinear_activation_params:
|
|
|
|
|
negative_slope: 0.1
|
|
|
|
|
use_weight_norm: True
|
|
|
|
|
use_spectral_norm: False
|
|
|
|
|
follow_official_norm: False
|
|
|
|
|
periods: [2, 3, 5, 7, 11]
|
|
|
|
|
period_discriminator_params:
|
|
|
|
|
in_channels: 1
|
|
|
|
|
out_channels: 1
|
|
|
|
|
kernel_sizes: [5, 3]
|
|
|
|
|
channels: 32
|
|
|
|
|
downsample_scales: [3, 3, 3, 3, 1]
|
|
|
|
|
max_downsample_channels: 1024
|
|
|
|
|
bias: True
|
|
|
|
|
nonlinear_activation: "leakyrelu"
|
|
|
|
|
nonlinear_activation_params:
|
|
|
|
|
negative_slope: 0.1
|
|
|
|
|
use_weight_norm: True
|
|
|
|
|
use_spectral_norm: False
|
|
|
|
|
# others
|
|
|
|
|
sampling_rate: 22050 # needed in the inference for saving wav
|
|
|
|
|
cache_generator_outputs: True # whether to cache generator outputs in the training
|
|
|
|
|
|
|
|
|
|
###########################################################
|
|
|
|
|
# LOSS SETTING #
|
|
|
|
|
###########################################################
|
|
|
|
|
# loss function related
|
|
|
|
|
generator_adv_loss_params:
|
|
|
|
|
average_by_discriminators: False # whether to average loss value by #discriminators
|
|
|
|
|
loss_type: mse # loss type, "mse" or "hinge"
|
|
|
|
|
discriminator_adv_loss_params:
|
|
|
|
|
average_by_discriminators: False # whether to average loss value by #discriminators
|
|
|
|
|
loss_type: mse # loss type, "mse" or "hinge"
|
|
|
|
|
feat_match_loss_params:
|
|
|
|
|
average_by_discriminators: False # whether to average loss value by #discriminators
|
|
|
|
|
average_by_layers: False # whether to average loss value by #layers of each discriminator
|
|
|
|
|
include_final_outputs: True # whether to include final outputs for loss calculation
|
|
|
|
|
mel_loss_params:
|
|
|
|
|
fs: 22050 # must be the same as the training data
|
|
|
|
|
fft_size: 1024 # fft points
|
|
|
|
|
hop_size: 256 # hop size
|
|
|
|
|
win_length: null # window length
|
|
|
|
|
window: hann # window type
|
|
|
|
|
num_mels: 80 # number of Mel basis
|
|
|
|
|
fmin: 0 # minimum frequency for Mel basis
|
|
|
|
|
fmax: null # maximum frequency for Mel basis
|
|
|
|
|
log_base: null # null represent natural log
|
|
|
|
|
|
|
|
|
|
###########################################################
|
|
|
|
|
# ADVERSARIAL LOSS SETTING #
|
|
|
|
|
###########################################################
|
|
|
|
|
lambda_adv: 1.0 # loss scaling coefficient for adversarial loss
|
|
|
|
|
lambda_mel: 45.0 # loss scaling coefficient for Mel loss
|
|
|
|
|
lambda_feat_match: 2.0 # loss scaling coefficient for feat match loss
|
|
|
|
|
lambda_dur: 1.0 # loss scaling coefficient for duration loss
|
|
|
|
|
lambda_kl: 1.0 # loss scaling coefficient for KL divergence loss
|
|
|
|
|
# others
|
|
|
|
|
sampling_rate: 22050 # needed in the inference for saving wav
|
|
|
|
|
cache_generator_outputs: True # whether to cache generator outputs in the training
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
###########################################################
|
|
|
|
|
# DATA LOADER SETTING #
|
|
|
|
|
###########################################################
|
|
|
|
|
batch_size: 64 # Batch size.
|
|
|
|
|
num_workers: 4 # Number of workers in DataLoader.
|
|
|
|
|
|
|
|
|
|
##########################################################
|
|
|
|
|
# OPTIMIZER & SCHEDULER SETTING #
|
|
|
|
|
##########################################################
|
|
|
|
|
# optimizer setting for generator
|
|
|
|
|
generator_optimizer_params:
|
|
|
|
|
beta1: 0.8
|
|
|
|
|
beta2: 0.99
|
|
|
|
|
epsilon: 1.0e-9
|
|
|
|
|
weight_decay: 0.0
|
|
|
|
|
generator_scheduler: exponential_decay
|
|
|
|
|
generator_scheduler_params:
|
|
|
|
|
learning_rate: 2.0e-4
|
|
|
|
|
gamma: 0.999875
|
|
|
|
|
|
|
|
|
|
# optimizer setting for discriminator
|
|
|
|
|
discriminator_optimizer_params:
|
|
|
|
|
beta1: 0.8
|
|
|
|
|
beta2: 0.99
|
|
|
|
|
epsilon: 1.0e-9
|
|
|
|
|
weight_decay: 0.0
|
|
|
|
|
discriminator_scheduler: exponential_decay
|
|
|
|
|
discriminator_scheduler_params:
|
|
|
|
|
learning_rate: 2.0e-4
|
|
|
|
|
gamma: 0.999875
|
|
|
|
|
generator_first: False # whether to start updating generator first
|
|
|
|
|
|
|
|
|
|
##########################################################
|
|
|
|
|
# OTHER TRAINING SETTING #
|
|
|
|
|
##########################################################
|
|
|
|
|
num_snapshots: 10 # max number of snapshots to keep while training
|
|
|
|
|
train_max_steps: 350000 # Number of training steps. == total_iters / ngpus, total_iters = 1000000
|
|
|
|
|
save_interval_steps: 1000 # Interval steps to save checkpoint.
|
|
|
|
|
eval_interval_steps: 250 # Interval steps to evaluate the network.
|
|
|
|
|
seed: 777 # random seed number
|
