Spaces:
Runtime error
Runtime error
| # This is the configuration file for LibriTTS dataset. | |
| # This configuration is based on StyleMelGAN paper but | |
| # uses MSE loss instead of Hinge loss. And I found that | |
| # batch_size = 8 is also working good. So maybe if you | |
| # want to accelerate the training, you can reduce the | |
| # batch size (e.g. 8 or 16). Upsampling scales is modified | |
| # to fit the shift size 300 pt. | |
| ########################################################### | |
| # 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: 60 # 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: "StyleMelGANGenerator" # Generator type. | |
| generator_params: | |
| in_channels: 128 | |
| aux_channels: 80 | |
| channels: 64 | |
| out_channels: 1 | |
| kernel_size: 9 | |
| dilation: 2 | |
| bias: True | |
| noise_upsample_scales: [10, 2, 2, 2] | |
| noise_upsample_activation: "LeakyReLU" | |
| noise_upsample_activation_params: | |
| negative_slope: 0.2 | |
| upsample_scales: [5, 1, 5, 1, 3, 1, 2, 2, 1] | |
| upsample_mode: "nearest" | |
| gated_function: "softmax" | |
| use_weight_norm: True | |
| ########################################################### | |
| # DISCRIMINATOR NETWORK ARCHITECTURE SETTING # | |
| ########################################################### | |
| discriminator_type: "StyleMelGANDiscriminator" # Discriminator type. | |
| discriminator_params: | |
| repeats: 4 | |
| window_sizes: [512, 1024, 2048, 4096] | |
| pqmf_params: | |
| - [1, None, None, None] | |
| - [2, 62, 0.26700, 9.0] | |
| - [4, 62, 0.14200, 9.0] | |
| - [8, 62, 0.07949, 9.0] | |
| discriminator_params: | |
| out_channels: 1 | |
| kernel_sizes: [5, 3] | |
| channels: 16 | |
| max_downsample_channels: 512 | |
| bias: True | |
| downsample_scales: [4, 4, 4, 1] | |
| nonlinear_activation: "LeakyReLU" | |
| nonlinear_activation_params: | |
| negative_slope: 0.2 | |
| use_weight_norm: True | |
| ########################################################### | |
| # 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" # Window function for STFT-based loss | |
| lambda_aux: 1.0 # Loss balancing coefficient for aux loss. | |
| ########################################################### | |
| # ADVERSARIAL LOSS SETTING # | |
| ########################################################### | |
| lambda_adv: 1.0 # Loss balancing coefficient for adv loss. | |
| 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. | |
| ########################################################### | |
| # DATA LOADER SETTING # | |
| ########################################################### | |
| batch_size: 32 # Batch size. | |
| batch_max_steps: 24000 # 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: 1.0e-4 | |
| betas: [0.5, 0.9] | |
| weight_decay: 0.0 | |
| generator_scheduler_type: MultiStepLR | |
| generator_scheduler_params: | |
| gamma: 0.5 | |
| milestones: | |
| - 100000 | |
| - 300000 | |
| - 500000 | |
| - 700000 | |
| - 900000 | |
| 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 # | |
| ########################################################### | |
| discriminator_train_start_steps: 100000 # Number of steps to start to train discriminator. | |
| train_max_steps: 1500000 # Number of training steps. | |
| save_interval_steps: 50000 # 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. | |