sampling_rate: 44100
hop_size: 512 # Hop size.
format: "npy"

model_type: "multiband_melgan_generator"

multiband_melgan_generator_params:
    out_channels: 4 # Number of output channels (number of subbands).
    kernel_size: 7 # Kernel size of initial and final conv layers.
    filters: 384 # Initial number of channels for conv layers.
    upsample_scales: [8, 4, 4] # List of Upsampling scales.
    stack_kernel_size: 3 # Kernel size of dilated conv layers in residual stack.
    stacks: 4 # Number of stacks in a single residual stack module.
    is_weight_norm: false # Use weight-norm or not.

multiband_melgan_discriminator_params:
    out_channels: 1 # Number of output channels.
    scales: 3 # Number of multi-scales.
    downsample_pooling: "AveragePooling1D" # Pooling type for the input downsampling.
    downsample_pooling_params: # Parameters of the above pooling function.
        pool_size: 4
        strides: 2
    kernel_sizes: [5, 3] # List of kernel size.
    filters: 16 # Number of channels of the initial conv layer.
    max_downsample_filters: 512 # Maximum number of channels of downsampling layers.
    downsample_scales: [4, 4, 4] # List of downsampling scales.
    nonlinear_activation: "LeakyReLU" # Nonlinear activation function.
    nonlinear_activation_params: # Parameters of nonlinear activation function.
        alpha: 0.2
    is_weight_norm: false # Use weight-norm or not.

hifigan_discriminator_params:
    out_channels: 1 # Number of output channels (number of subbands).
    period_scales: [3, 5, 7, 11, 17, 23, 37] # List of period scales.
    n_layers: 5 # Number of layer of each period discriminator.
    kernel_size: 5 # Kernel size.
    strides: 3 # Strides
    filters: 8 # In Conv filters of each period discriminator
    filter_scales: 4 # Filter scales.
    max_filters: 512 # maximum filters of period discriminator's conv.
    is_weight_norm: false # Use weight-norm or not.

stft_loss_params:
    fft_lengths: [1024, 2048, 512] # List of FFT size for STFT-based loss.
    frame_steps: [120, 240, 50] # List of hop size for STFT-based loss
    frame_lengths: [600, 1200, 240] # List of window length for STFT-based loss.

subband_stft_loss_params:
    fft_lengths: [384, 683, 171] # List of FFT size for STFT-based loss.
    frame_steps: [30, 60, 10] # List of hop size for STFT-based loss
    frame_lengths: [150, 300, 60] # List of window length for STFT-based loss.

lambda_feat_match: 10.0 # Loss balancing coefficient for feature matching loss
lambda_adv: 2.5 # Loss balancing coefficient for adversarial loss.

batch_size: 32 # Batch size for each GPU with assuming that gradient_accumulation_steps == 1.
eval_batch_size: 16
batch_max_steps: 8192 # Length of each audio in batch for training. Make sure dividable by hop_size.
batch_max_steps_valid: 8192 # Length of each audio for validation. Make sure dividable by hope_size.
remove_short_samples: true # 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.
is_shuffle: false # shuffle dataset after each epoch.

generator_optimizer_params:
    lr_fn: "PiecewiseConstantDecay"
    lr_params:
        boundaries: [100000, 200000, 300000, 400000, 500000, 600000, 700000]
        values:
            [
                0.0005,
                0.0005,
                0.00025,
                0.000125,
                0.0000625,
                0.00003125,
                0.000015625,
                0.000001,
            ]
    amsgrad: false

discriminator_optimizer_params:
    lr_fn: "PiecewiseConstantDecay"
    lr_params:
        boundaries: [100000, 200000, 300000, 400000, 500000]
        values: [0.00025, 0.000125, 0.0000625, 0.00003125, 0.000015625, 0.000001]
    amsgrad: false

gradient_accumulation_steps: 1

discriminator_train_start_steps: 200000 # steps begin training discriminator
train_max_steps: 1000000 # Number of training steps.
save_interval_steps: 20000 # Interval steps to save checkpoint.
eval_interval_steps: 5000 # Interval steps to evaluate the network.
log_interval_steps: 200 # Interval steps to record the training log.