PaddleSpeech/examples/csmsc/voc1/conf/default.yaml

# This is the hyperparameter configuration file for Parallel WaveGAN.
# Please make sure this is adjusted for the CSMSC dataset. If you want to
# apply to the other dataset, you might need to carefully change some parameters.
# This configuration requires 12 GB GPU memory and takes ~3 days on RTX TITAN.

###########################################################
#                FEATURE EXTRACTION SETTING               #
###########################################################
fs: 24000                # Sampling rate.
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.
n_mels: 80               # Number of mel basis.
fmin: 80                 # Minimum freq in mel basis calculation. (Hz)
fmax: 7600               # Maximum frequency in mel basis calculation. (Hz)


###########################################################
#         GENERATOR NETWORK ARCHITECTURE SETTING          #
###########################################################
generator_params:
    in_channels: 1        # Number of input channels.
    out_channels: 1       # Number of output channels.
    kernel_size: 3        # Kernel size of dilated convolution.
    layers: 30            # Number of residual block layers.
    stacks: 3             # Number of stacks i.e., dilation cycles.
    residual_channels: 64 # Number of channels in residual conv.
    gate_channels: 128    # Number of channels in gated conv.
    skip_channels: 64     # Number of channels in skip conv.
    aux_channels: 80      # Number of channels for auxiliary feature conv.
                          # Must be the same as num_mels.
    aux_context_window: 2 # Context window size for auxiliary feature.
                          # If set to 2, previous 2 and future 2 frames will be considered.
    dropout: 0.0          # Dropout rate. 0.0 means no dropout applied.
    bias: true            # use bias in residual blocks
    use_weight_norm: true # Whether to use weight norm.
                          # If set to true, it will be applied to all of the conv layers.
    use_causal_conv: false               # use causal conv in residual blocks and upsample layers
    upsample_scales: [4, 5, 3, 5]     # Upsampling scales. Prodcut of these must be the same as hop size.
    interpolate_mode: "nearest" # upsample net interpolate mode
    freq_axis_kernel_size: 1 # upsamling net: convolution kernel size in frequencey axis
    nonlinear_activation: null
    nonlinear_activation_params: {}

###########################################################
#       DISCRIMINATOR NETWORK ARCHITECTURE SETTING        #
###########################################################
discriminator_params:
    in_channels: 1        # Number of input channels.
    out_channels: 1       # Number of output channels.
    kernel_size: 3        # Number of output channels.
    layers: 10            # Number of conv layers.
    conv_channels: 64     # Number of chnn layers.
    bias: true            # Whether to use bias parameter in conv.
    use_weight_norm: true # Whether to use weight norm.
                          # If set to true, it will be applied to all of the conv layers.
    nonlinear_activation: "leakyrelu" # Nonlinear function after each conv.
    nonlinear_activation_params:      # Nonlinear function parameters
        negative_slope: 0.2           # Alpha in leakyrelu.

###########################################################
#                   STFT LOSS SETTING                     #
###########################################################
stft_loss_params:
    fft_sizes: [1024, 2048, 512]  # List of FFT size for STFT-based loss.
    hop_sizes: [120, 240, 50]     # List of hop size for STFT-based loss
    win_lengths: [600, 1200, 240] # List of window length for STFT-based loss.
    window: "hann"         # Window function for STFT-based loss

###########################################################
#               ADVERSARIAL LOSS SETTING                  #
###########################################################
lambda_adv: 4.0  # Loss balancing coefficient.

###########################################################
#                  DATA LOADER SETTING                    #
###########################################################
batch_size: 8              # Batch size.
batch_max_steps: 25500     # Length of each audio in batch. Make sure dividable by n_shift.
num_workers: 2             # Number of workers in DataLoader.

###########################################################
#             OPTIMIZER & SCHEDULER SETTING               #
###########################################################
generator_optimizer_params:
    epsilon: 1.0e-6        # Generator's epsilon.
    weight_decay: 0.0      # Generator's weight decay coefficient.
generator_scheduler_params:
    learning_rate: 0.0001  # Generator's learning rate.
    step_size: 200000      # Generator's scheduler step size.
    gamma: 0.5             # Generator's scheduler gamma.
                           # At each step size, lr will be multiplied by this parameter.
generator_grad_norm: 10    # Generator's gradient norm.
discriminator_optimizer_params:
    epsilon: 1.0e-6            # Discriminator's epsilon.
    weight_decay: 0.0          # Discriminator's weight decay coefficient.
discriminator_scheduler_params:
    learning_rate: 0.00005     # Discriminator's learning rate.
    step_size: 200000          # Discriminator's scheduler step size.
    gamma: 0.5                 # Discriminator's scheduler gamma.
                               # At each step size, lr will be multiplied by this parameter.
discriminator_grad_norm: 1     # Discriminator's gradient norm.

###########################################################
#                    INTERVAL SETTING                     #
###########################################################
discriminator_train_start_steps: 100000 # Number of steps to start to train discriminator.
train_max_steps: 400000                 # Number of training steps.
save_interval_steps: 5000               # Interval steps to save checkpoint.
eval_interval_steps: 1000               # Interval steps to evaluate the network.

###########################################################
#                     OTHER SETTING                       #
###########################################################
num_save_intermediate_results: 4  # Number of results to be saved as intermediate results.
num_snapshots: 10                 # max number of snapshots to keep while training
seed: 42                          # random seed for paddle, random, and np.random