ParallelWaveGAN/egs/libritts/voc1/conf/hifigan.v1.yaml

# This is the configuration file for LibriTTS dataset.
# This configuration is based on HiFiGAN V1, which is
# an official configuration. But I found that the optimizer
# setting does not work well with my implementation.
# So I changed optimizer settings as follows:
# - AdamW -> Adam
# - betas: [0.8, 0.99] -> betas: [0.5, 0.9]
# - Scheduler: ExponentialLR -> MultiStepLR
# To match the shift size difference, the upsample scales
# is also modified from the original 256 shift setting.

###########################################################
#                FEATURE EXTRACTION SETTING               #
###########################################################
sampling_rate: 24000     # Sampling rate.
fft_size: 2048           # FFT size.
hop_size: 300            # Hop size.
win_length: 1200         # Window length.
                         # If set to null, it will be the same as fft_size.
window: "hann"           # Window function.
num_mels: 80             # Number of mel basis.
fmin: 80                 # Minimum freq in mel basis calculation.
fmax: 7600               # Maximum frequency in mel basis calculation.
global_gain_scale: 1.0   # Will be multiplied to all of waveform.
trim_silence: false      # Whether to trim the start and end of silence.
trim_threshold_in_db: 20 # Need to tune carefully if the recording is not good.
trim_frame_size: 1024    # Frame size in trimming.
trim_hop_size: 256       # Hop size in trimming.
format: "hdf5"           # Feature file format. "npy" or "hdf5" is supported.

###########################################################
#         GENERATOR NETWORK ARCHITECTURE SETTING          #
###########################################################
generator_type: HiFiGANGenerator
generator_params:
    in_channels: 80                       # Number of input channels.
    out_channels: 1                       # Number of output channels.
    channels: 512                         # Number of initial channels.
    kernel_size: 7                        # Kernel size of initial and final conv layers.
    upsample_scales: [5, 5, 4, 3]         # Upsampling scales.
    upsample_kernel_sizes: [10, 10, 8, 6] # Kernel size for upsampling layers.
    resblock_kernel_sizes: [3, 7, 11]     # Kernel size for residual blocks.
    resblock_dilations:                   # Dilations for residual blocks.
        - [1, 3, 5]
        - [1, 3, 5]
        - [1, 3, 5]
    use_additional_convs: true            # Whether to use additional conv layer in residual blocks.
    bias: true                            # Whether to use bias parameter in conv.
    nonlinear_activation: "LeakyReLU"     # Nonlinear activation type.
    nonlinear_activation_params:          # Nonlinear activation paramters.
        negative_slope: 0.1
    use_weight_norm: true                 # Whether to apply weight normalization.

###########################################################
#       DISCRIMINATOR NETWORK ARCHITECTURE SETTING        #
###########################################################
discriminator_type: HiFiGANMultiScaleMultiPeriodDiscriminator
discriminator_params:
    scales: 3                              # Number of multi-scale discriminator.
    scale_downsample_pooling: "AvgPool1d"  # Pooling operation for scale discriminator.
    scale_downsample_pooling_params:
        kernel_size: 4                     # Pooling kernel size.
        stride: 2                          # Pooling stride.
        padding: 2                         # Padding size.
    scale_discriminator_params:
        in_channels: 1                     # Number of input channels.
        out_channels: 1                    # Number of output channels.
        kernel_sizes: [15, 41, 5, 3]       # List of kernel sizes.
        channels: 128                      # Initial number of channels.
        max_downsample_channels: 1024      # Maximum number of channels in downsampling conv layers.
        max_groups: 16                     # Maximum number of groups in downsampling conv layers.
        bias: true
        downsample_scales: [4, 4, 4, 4, 1] # Downsampling scales.
        nonlinear_activation: "LeakyReLU"  # Nonlinear activation.
        nonlinear_activation_params:
            negative_slope: 0.1
    follow_official_norm: true             # Whether to follow the official norm setting.
    periods: [2, 3, 5, 7, 11]              # List of period for multi-period discriminator.
    period_discriminator_params:
        in_channels: 1                     # Number of input channels.
        out_channels: 1                    # Number of output channels.
        kernel_sizes: [5, 3]               # List of kernel sizes.
        channels: 32                       # Initial number of channels.
        downsample_scales: [3, 3, 3, 3, 1] # Downsampling scales.
        max_downsample_channels: 1024      # Maximum number of channels in downsampling conv layers.
        bias: true                         # Whether to use bias parameter in conv layer."
        nonlinear_activation: "LeakyReLU"  # Nonlinear activation.
        nonlinear_activation_params:       # Nonlinear activation paramters.
            negative_slope: 0.1
        use_weight_norm: true              # Whether to apply weight normalization.
        use_spectral_norm: false           # Whether to apply spectral normalization.

###########################################################
#                   STFT LOSS SETTING                     #
###########################################################
use_stft_loss: false                 # Whether to use multi-resolution STFT loss.
use_mel_loss: true                   # Whether to use Mel-spectrogram loss.
mel_loss_params:
    fs: 24000
    fft_size: 2048
    hop_size: 300
    win_length: 1200
    window: "hann"
    num_mels: 80
    fmin: 0
    fmax: 12000
    log_base: null
generator_adv_loss_params:
    average_by_discriminators: false # Whether to average loss by #discriminators.
discriminator_adv_loss_params:
    average_by_discriminators: false # Whether to average loss by #discriminators.
use_feat_match_loss: true
feat_match_loss_params:
    average_by_discriminators: false # Whether to average loss by #discriminators.
    average_by_layers: false         # Whether to average loss by #layers in each discriminator.
    include_final_outputs: false     # Whether to include final outputs in feat match loss calculation.

###########################################################
#               ADVERSARIAL LOSS SETTING                  #
###########################################################
lambda_aux: 45.0       # Loss balancing coefficient for STFT loss.
lambda_adv: 1.0        # Loss balancing coefficient for adversarial loss.
lambda_feat_match: 2.0 # Loss balancing coefficient for feat match loss..

###########################################################
#                  DATA LOADER SETTING                    #
###########################################################
batch_size: 16              # Batch size.
batch_max_steps: 8400       # Length of each audio in batch. Make sure dividable by hop_size.
pin_memory: true            # Whether to pin memory in Pytorch DataLoader.
num_workers: 2              # Number of workers in Pytorch DataLoader.
remove_short_samples: false # Whether to remove samples the length of which are less than batch_max_steps.
allow_cache: false          # Whether to allow cache in dataset. If true, it requires cpu memory.

###########################################################
#             OPTIMIZER & SCHEDULER SETTING               #
###########################################################
generator_optimizer_type: Adam
generator_optimizer_params:
    lr: 2.0e-4
    betas: [0.5, 0.9]
    weight_decay: 0.0
generator_scheduler_type: MultiStepLR
generator_scheduler_params:
    gamma: 0.5
    milestones:
        - 200000
        - 400000
        - 600000
        - 800000
generator_grad_norm: -1
discriminator_optimizer_type: Adam
discriminator_optimizer_params:
    lr: 2.0e-4
    betas: [0.5, 0.9]
    weight_decay: 0.0
discriminator_scheduler_type: MultiStepLR
discriminator_scheduler_params:
    gamma: 0.5
    milestones:
        - 200000
        - 400000
        - 600000
        - 800000
discriminator_grad_norm: -1

###########################################################
#                    INTERVAL SETTING                     #
###########################################################
generator_train_start_steps: 1     # Number of steps to start to train discriminator.
discriminator_train_start_steps: 0 # Number of steps to start to train discriminator.
train_max_steps: 2500000           # Number of training steps.
save_interval_steps: 10000         # Interval steps to save checkpoint.
eval_interval_steps: 1000          # Interval steps to evaluate the network.
log_interval_steps: 100            # Interval steps to record the training log.

###########################################################
#                     OTHER SETTING                       #
###########################################################
num_save_intermediate_results: 4  # Number of results to be saved as intermediate results.