| allow_cache: true | |
| batch_max_steps: 8192 | |
| batch_size: 16 | |
| config: conf/parallel_wavegan.v3.yaml | |
| dev_dumpdir: dump/dev/norm | |
| dev_feats_scp: null | |
| dev_segments: null | |
| dev_wav_scp: null | |
| discriminator_grad_norm: 1 | |
| discriminator_optimizer_params: | |
| eps: 1.0e-06 | |
| lr: 5.0e-05 | |
| weight_decay: 0.0 | |
| discriminator_params: | |
| channels: 16 | |
| downsample_pooling: AvgPool1d | |
| downsample_pooling_params: | |
| count_include_pad: false | |
| kernel_size: 4 | |
| padding: 1 | |
| stride: 2 | |
| downsample_scales: | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| in_channels: 1 | |
| kernel_sizes: | |
| - 5 | |
| - 3 | |
| max_downsample_channels: 1024 | |
| nonlinear_activation: LeakyReLU | |
| nonlinear_activation_params: | |
| negative_slope: 0.2 | |
| out_channels: 1 | |
| scales: 3 | |
| use_weight_norm: true | |
| discriminator_scheduler_params: | |
| gamma: 0.5 | |
| step_size: 3000000 | |
| discriminator_train_start_steps: 0 | |
| discriminator_type: MelGANMultiScaleDiscriminator | |
| distributed: false | |
| eval_interval_steps: 1000 | |
| fft_size: 1024 | |
| fmax: 7600 | |
| fmin: 80 | |
| format: hdf5 | |
| generator_grad_norm: 10 | |
| generator_optimizer_params: | |
| eps: 1.0e-06 | |
| lr: 0.0001 | |
| weight_decay: 0.0 | |
| generator_params: | |
| aux_channels: 80 | |
| aux_context_window: 2 | |
| dropout: 0.0 | |
| gate_channels: 128 | |
| in_channels: 1 | |
| kernel_size: 5 | |
| layers: 30 | |
| out_channels: 1 | |
| residual_channels: 64 | |
| skip_channels: 64 | |
| stacks: 3 | |
| upsample_net: ConvInUpsampleNetwork | |
| upsample_params: | |
| upsample_scales: | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| use_weight_norm: true | |
| generator_scheduler_params: | |
| gamma: 0.5 | |
| step_size: 3000000 | |
| global_gain_scale: 1.0 | |
| hop_size: 256 | |
| lambda_adv: 4.0 | |
| lambda_feat_match: 25.0 | |
| log_interval_steps: 100 | |
| num_mels: 80 | |
| num_save_intermediate_results: 4 | |
| num_workers: 2 | |
| outdir: exp/train_nodev_parallel_wavegan.v3_ljspeech_parallel_wavegan.v3 | |
| pin_memory: true | |
| pretrain: downloads/ljspeech_parallel_wavegan.v3/checkpoint-3000000steps.pkl | |
| rank: 0 | |
| remove_short_samples: true | |
| resume: '' | |
| sampling_rate: 22050 | |
| save_interval_steps: 5000 | |
| stft_loss_params: | |
| fft_sizes: | |
| - 1024 | |
| - 2048 | |
| - 512 | |
| hop_sizes: | |
| - 120 | |
| - 240 | |
| - 50 | |
| win_lengths: | |
| - 600 | |
| - 1200 | |
| - 240 | |
| window: hann_window | |
| train_dumpdir: dump/train_nodev/norm | |
| train_feats_scp: null | |
| train_max_steps: 50000 | |
| train_segments: null | |
| train_wav_scp: null | |
| trim_frame_size: 2048 | |
| trim_hop_size: 512 | |
| trim_silence: true | |
| trim_threshold_in_db: 60 | |
| use_feat_match_loss: true | |
| verbose: 1 | |
| version: 0.4.8 | |
| win_length: null | |
| window: hann | |