| backbone: | |
| class_path: vocos.models.VocosBackbone | |
| init_args: | |
| adanorm_num_embeddings: null | |
| dim: 1024 | |
| input_channels: 128 | |
| intermediate_dim: 2048 | |
| layer_scale_init_value: null | |
| num_layers: 8 | |
| decay_mel_coeff: false | |
| enable_discriminator: true | |
| evaluate_periodicty: true | |
| evaluate_pesq: true | |
| evaluate_utmos: true | |
| feature_extractor: | |
| class_path: vocos.feature_extractors.MelSpectrogramFeatures | |
| init_args: | |
| hop_length: 256 | |
| n_fft: 2048 | |
| n_mels: 128 | |
| padding: center | |
| sample_rate: 48000 | |
| generator_period: 3 | |
| grad_acc: 1 | |
| head: | |
| class_path: vocos.heads.ISTFTHead | |
| init_args: | |
| dim: 1024 | |
| hop_length: 256 | |
| n_fft: 2048 | |
| padding: center | |
| initial_learning_rate: 0.0003 | |
| mel_loss_coeff: 15.0 | |
| mrd_loss_coeff: 0.1 | |
| num_warmup_steps: 500 | |
| pretrain_decoupled_steps: 0 | |
| pretrain_disc_steps: 500 | |
| pretrain_mel_steps: 0 | |
| pretrained_ckpt: null | |
| sample_rate: 48000 | |