| # pytorch_lightning==1.8.6 | |
| seed_everything: 4444 | |
| data: | |
| class_path: vocos.dataset.VocosDataModule | |
| init_args: | |
| train_params: | |
| filelist_path: "/home/ubuntu/vocos/data/filelist2.train" | |
| sampling_rate: 24000 | |
| num_samples: 57600 | |
| batch_size: 64 | |
| num_workers: 8 | |
| val_params: | |
| filelist_path: "/home/ubuntu/vocos/data/filelist.val" | |
| sampling_rate: 24000 | |
| num_samples: 57600 | |
| batch_size: 16 | |
| num_workers: 8 | |
| model: | |
| class_path: vocos.experiment.VocosExp | |
| init_args: | |
| sample_rate: 24000 | |
| initial_learning_rate: 5e-4 | |
| mel_loss_coeff: 45 | |
| mrd_loss_coeff: 0.1 | |
| num_warmup_steps: 0 # Optimizers warmup steps | |
| pretrain_mel_steps: 0 # 0 means GAN objective from the first iteration | |
| # automatic evaluation | |
| evaluate_utmos: true | |
| evaluate_pesq: true | |
| evaluate_periodicty: true | |
| feature_extractor: | |
| class_path: vocos.feature_extractors.MelSpectrogramFeatures | |
| init_args: | |
| sample_rate: 24000 | |
| n_fft: 2048 | |
| hop_length: 300 | |
| win_length: 1200 | |
| n_mels: 80 | |
| padding: center | |
| backbone: | |
| class_path: vocos.models.VocosBackbone | |
| init_args: | |
| input_channels: 80 | |
| dim: 512 | |
| intermediate_dim: 1536 | |
| num_layers: 8 | |
| head: | |
| class_path: vocos.heads.ISTFTHead | |
| init_args: | |
| dim: 512 | |
| n_fft: 2048 | |
| hop_length: 300 | |
| padding: center | |
| trainer: | |
| logger: | |
| class_path: pytorch_lightning.loggers.TensorBoardLogger | |
| init_args: | |
| save_dir: logs/ | |
| callbacks: | |
| - class_path: pytorch_lightning.callbacks.LearningRateMonitor | |
| - class_path: pytorch_lightning.callbacks.ModelSummary | |
| init_args: | |
| max_depth: 2 | |
| - class_path: pytorch_lightning.callbacks.ModelCheckpoint | |
| init_args: | |
| # every_n_train_steps: 5000 | |
| # filename: vocos_checkpoint_step_{step} | |
| monitor: val_loss | |
| filename: vocos_checkpoint_{epoch}_{step}_{val_loss:.4f} | |
| save_top_k: 3 | |
| save_last: true | |
| - class_path: vocos.helpers.GradNormCallback | |
| # Lightning calculates max_steps across all optimizer steps (rather than number of batches) | |
| # This equals to 1M steps per generator and 1M per discriminator | |
| max_steps: 2000000 | |
| # You might want to limit val batches when evaluating all the metrics, as they are time-consuming | |
| limit_val_batches: 50 | |
| accelerator: gpu | |
| strategy: ddp | |
| devices: [0,1] | |
| log_every_n_steps: 100 | |