| audio: | |
| chunk_size: 261120 | |
| dim_f: 4096 | |
| dim_t: 256 | |
| hop_length: 1024 | |
| n_fft: 8192 | |
| num_channels: 2 | |
| sample_rate: 44100 | |
| min_mean_abs: 0.001 | |
| model: | |
| act: gelu | |
| bottleneck_factor: 4 | |
| growth: 128 | |
| norm: InstanceNorm | |
| num_blocks_per_scale: 2 | |
| num_channels: 128 | |
| num_scales: 5 | |
| num_subbands: 4 | |
| scale: | |
| - 2 | |
| - 2 | |
| training: | |
| batch_size: 6 | |
| gradient_accumulation_steps: 6 | |
| grad_clip: 0 | |
| instruments: | |
| - vocals | |
| - bass | |
| - drums | |
| - other | |
| lr: 5.0e-05 | |
| patience: 3 | |
| reduce_factor: 0.95 | |
| target_instrument: null | |
| num_epochs: 1000 | |
| num_steps: 1000 | |
| augmentation: false # enable augmentations by audiomentations and pedalboard | |
| augmentation_type: simple1 | |
| use_mp3_compress: false # Deprecated | |
| augmentation_mix: true # Mix several stems of the same type with some probability | |
| augmentation_loudness: true # randomly change loudness of each stem | |
| augmentation_loudness_type: 2 # Type 1 or 2 | |
| augmentation_loudness_min: 0.8 | |
| augmentation_loudness_max: 1.2 | |
| q: 0.95 | |
| coarse_loss_clip: true | |
| ema_momentum: 0.999 | |
| optimizer: adam | |
| other_fix: false # it's needed for checking on multisong dataset if other is actually instrumental | |
| inference: | |
| batch_size: 1 | |
| dim_t: 256 | |
| num_overlap: 4 |