| 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 | |
| grad_clip: 0 | |
| instruments: | |
| - Vocals | |
| - Instrumental | |
| lr: 1.0e-05 | |
| patience: 2 | |
| reduce_factor: 0.95 | |
| target_instrument: null | |
| num_epochs: 1000 | |
| num_steps: 1000 | |
| augmentation: 1 | |
| augmentation_type: simple1 | |
| augmentation_mix: true | |
| q: 0.95 | |
| coarse_loss_clip: true | |
| ema_momentum: 0.999 | |
| inference: | |
| batch_size: 1 | |
| dim_t: 256 | |
| num_overlap: 8 |