| audio: | |
| chunk_size: 131584 | |
| dim_f: 1024 | |
| dim_t: 256 | |
| hop_length: 512 | |
| n_fft: 2048 | |
| num_channels: 2 | |
| sample_rate: 44100 | |
| min_mean_abs: 0.001 | |
| model: | |
| dim: 192 | |
| depth: 6 | |
| stereo: true | |
| num_stems: 1 | |
| time_transformer_depth: 1 | |
| freq_transformer_depth: 1 | |
| linear_transformer_depth: 0 | |
| freqs_per_bands: !!python/tuple | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 2 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 12 | |
| - 12 | |
| - 12 | |
| - 12 | |
| - 12 | |
| - 12 | |
| - 12 | |
| - 12 | |
| - 24 | |
| - 24 | |
| - 24 | |
| - 24 | |
| - 24 | |
| - 24 | |
| - 24 | |
| - 24 | |
| - 48 | |
| - 48 | |
| - 48 | |
| - 48 | |
| - 48 | |
| - 48 | |
| - 48 | |
| - 48 | |
| - 128 | |
| - 129 | |
| dim_head: 64 | |
| heads: 8 | |
| attn_dropout: 0.1 | |
| ff_dropout: 0.1 | |
| flash_attn: true | |
| dim_freqs_in: 1025 | |
| stft_n_fft: 2048 | |
| stft_hop_length: 512 | |
| stft_win_length: 2048 | |
| stft_normalized: false | |
| mask_estimator_depth: 2 | |
| multi_stft_resolution_loss_weight: 1.0 | |
| multi_stft_resolutions_window_sizes: !!python/tuple | |
| - 4096 | |
| - 2048 | |
| - 1024 | |
| - 512 | |
| - 256 | |
| multi_stft_hop_size: 147 | |
| multi_stft_normalized: False | |
| mlp_expansion_factor: 4 # Probably too big (requires a lot of memory for weights) | |
| use_torch_checkpoint: False # it allows to greatly reduce GPU memory consumption during training (not fully tested) | |
| skip_connection: False # Enable skip connection between transformer blocks - can solve problem with gradients and probably faster training | |
| training: | |
| batch_size: 10 | |
| gradient_accumulation_steps: 1 | |
| grad_clip: 0 | |
| instruments: | |
| - vocals | |
| - bass | |
| - drums | |
| - other | |
| lr: 5.0e-05 | |
| patience: 2 | |
| reduce_factor: 0.95 | |
| target_instrument: vocals | |
| num_epochs: 1000 | |
| num_steps: 1000 | |
| 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 | |
| use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true | |
| augmentations: | |
| enable: true # enable or disable all augmentations (to fast disable if needed) | |
| loudness: true # randomly change loudness of each stem on the range (loudness_min; loudness_max) | |
| loudness_min: 0.5 | |
| loudness_max: 1.5 | |
| inference: | |
| batch_size: 1 | |
| dim_t: 256 | |
| num_overlap: 4 |