Spaces:
Runtime error
Runtime error
| # This is the hyperparameter configuration file for MelGAN. | |
| # Please make sure this is adjusted for the LJSpeech dataset. If you want to | |
| # apply to the other dataset, you might need to carefully change some parameters. | |
| # Both generator and discriminator are based on MelGAN but we also use | |
| # STFT-based auxiliary loss with fixed lr. This configuration requires ~4 GB | |
| # GPU memory and takes ~4 days on TITAN V. | |
| # The discriminator loss is not stable as v1, i.e., gradually decreasing both | |
| # real and fake losses (Also, feature matching loss keeps increasing). But in | |
| # terms of naturalness, this model is better than v1. | |
| # If you get unstable results, please increase train_max_steps or use v3.long. | |
| ########################################################### | |
| # FEATURE EXTRACTION SETTING # | |
| ########################################################### | |
| sampling_rate: 22050 # Sampling rate. | |
| fft_size: 1024 # FFT size. | |
| hop_size: 256 # Hop size. | |
| win_length: null # 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: true # 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: 2048 # Frame size in trimming. | |
| trim_hop_size: 512 # Hop size in trimming. | |
| format: "hdf5" # Feature file format. "npy" or "hdf5" is supported. | |
| ########################################################### | |
| # GENERATOR NETWORK ARCHITECTURE SETTING # | |
| ########################################################### | |
| generator_type: "MelGANGenerator" # Generator type. | |
| generator_params: | |
| in_channels: 80 # Number of input channels. | |
| out_channels: 1 # Number of output channels. | |
| kernel_size: 7 # Kernel size of initial and final conv layers. | |
| channels: 512 # Initial number of channels for conv layers. | |
| upsample_scales: [8, 8, 2, 2] # List of Upsampling scales. | |
| stack_kernel_size: 3 # Kernel size of dilated conv layers in residual stack. | |
| stacks: 3 # Number of stacks in a single residual stack module. | |
| use_weight_norm: True # Whether to use weight normalization. | |
| use_causal_conv: False # Whether to use causal convolution. | |
| ########################################################### | |
| # DISCRIMINATOR NETWORK ARCHITECTURE SETTING # | |
| ########################################################### | |
| discriminator_type: "MelGANMultiScaleDiscriminator" # Discriminator type. | |
| discriminator_params: | |
| in_channels: 1 # Number of input channels. | |
| out_channels: 1 # Number of output channels. | |
| scales: 3 # Number of multi-scales. | |
| downsample_pooling: "AvgPool1d" # Pooling type for the input downsampling. | |
| downsample_pooling_params: # Parameters of the above pooling function. | |
| kernel_size: 4 | |
| stride: 2 | |
| padding: 1 | |
| count_include_pad: False | |
| kernel_sizes: [5, 3] # List of kernel size. | |
| channels: 16 # Number of channels of the initial conv layer. | |
| max_downsample_channels: 1024 # Maximum number of channels of downsampling layers. | |
| downsample_scales: [4, 4, 4, 4] # List of downsampling scales. | |
| nonlinear_activation: "LeakyReLU" # Nonlinear activation function. | |
| nonlinear_activation_params: # Parameters of nonlinear activation function. | |
| negative_slope: 0.2 | |
| use_weight_norm: True # Whether to use weight norm. | |
| ########################################################### | |
| # 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 | |
| ########################################################### | |
| # ADVERSARIAL LOSS SETTING # | |
| ########################################################### | |
| use_feat_match_loss: true # Whether to use feature matching loss. | |
| lambda_feat_match: 25.0 # Loss balancing coefficient for feature matching loss. | |
| lambda_adv: 4.0 # Loss balancing coefficient for adversarial loss. | |
| ########################################################### | |
| # DATA LOADER SETTING # | |
| ########################################################### | |
| batch_size: 16 # Batch size. | |
| batch_max_steps: 8192 # 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: 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. | |
| ########################################################### | |
| # OPTIMIZER & SCHEDULER SETTING # | |
| ########################################################### | |
| generator_optimizer_params: | |
| lr: 0.0001 # Generator's learning rate. | |
| eps: 1.0e-6 # Generator's epsilon. | |
| weight_decay: 0.0 # Generator's weight decay coefficient. | |
| generator_scheduler_params: | |
| step_size: 2000000 # 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: | |
| lr: 0.00005 # Discriminator's learning rate. | |
| eps: 1.0e-6 # Discriminator's epsilon. | |
| weight_decay: 0.0 # Discriminator's weight decay coefficient. | |
| discriminator_scheduler_params: | |
| step_size: 2000000 # 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: 2000000 # Number of training steps. | |
| save_interval_steps: 5000 # 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. | |