File size: 5,822 Bytes
14292f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
# This is the hyperparameter configuration file for Multi-Band MelGAN.
# Please make sure this is adjusted for the Baker dataset. If you want to
# apply to the other dataset, you might need to carefully change some parameters.
# This configuration performs 1000k iters.
###########################################################
# FEATURE EXTRACTION SETTING #
###########################################################
sampling_rate: 24000
hop_size: 300 # Hop size.
format: "npy"
###########################################################
# GENERATOR NETWORK ARCHITECTURE SETTING #
###########################################################
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: [3, 5, 5] # 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.
###########################################################
# DISCRIMINATOR NETWORK ARCHITECTURE SETTING #
###########################################################
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.
###########################################################
# STFT LOSS SETTING #
###########################################################
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.
###########################################################
# ADVERSARIAL LOSS SETTING #
###########################################################
lambda_feat_match: 10.0 # Loss balancing coefficient for feature matching loss
lambda_adv: 2.5 # Loss balancing coefficient for adversarial loss.
###########################################################
# DATA LOADER SETTING #
###########################################################
batch_size: 64 # Batch size for each GPU with assuming that gradient_accumulation_steps == 1.
batch_max_steps: 9600 # Length of each audio in batch for training. Make sure dividable by hop_size.
batch_max_steps_valid: 48000 # 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: true # Whether to allow cache in dataset. If true, it requires cpu memory.
is_shuffle: true # shuffle dataset after each epoch.
###########################################################
# OPTIMIZER & SCHEDULER SETTING #
###########################################################
generator_optimizer_params:
lr_fn: "PiecewiseConstantDecay"
lr_params:
boundaries: [100000, 200000, 300000, 400000, 500000, 600000, 700000]
values: [0.001, 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
###########################################################
# INTERVAL SETTING #
###########################################################
discriminator_train_start_steps: 200000 # steps begin training discriminator
train_max_steps: 4000000 # 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.
###########################################################
# OTHER SETTING #
###########################################################
num_save_intermediate_results: 1 # Number of batch to be saved as intermediate results. |