| audio: | |
| chunk_size: 261632 | |
| dim_f: 4096 | |
| dim_t: 512 | |
| hop_length: 512 | |
| n_fft: 8192 | |
| num_channels: 2 | |
| sample_rate: 44100 | |
| min_mean_abs: 0.000 | |
| model: | |
| encoder_name: maxvit_tiny_tf_512 # look with torchseg.list_encoders(). Currently 858 available | |
| decoder_type: unet # unet, fpn | |
| act: gelu | |
| num_channels: 128 | |
| num_subbands: 8 | |
| training: | |
| batch_size: 18 | |
| gradient_accumulation_steps: 1 | |
| grad_clip: 1.0 | |
| instruments: | |
| - vocals | |
| - other | |
| lr: 1.0e-04 | |
| patience: 2 | |
| reduce_factor: 0.95 | |
| target_instrument: null | |
| num_epochs: 1000 | |
| num_steps: 1000 | |
| q: 0.95 | |
| coarse_loss_clip: true | |
| ema_momentum: 0.999 | |
| optimizer: radam | |
| other_fix: true # 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: false # 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 | |
| mixup: true # mix several stems of same type with some probability (only works for dataset types: 1, 2, 3) | |
| mixup_probs: !!python/tuple # 2 additional stems of the same type (1st with prob 0.2, 2nd with prob 0.02) | |
| - 0.2 | |
| - 0.02 | |
| mixup_loudness_min: 0.5 | |
| mixup_loudness_max: 1.5 | |
| all: | |
| channel_shuffle: 0.5 # Set 0 or lower to disable | |
| random_inverse: 0.1 # inverse track (better lower probability) | |
| random_polarity: 0.5 # polarity change (multiply waveform to -1) | |
| inference: | |
| batch_size: 8 | |
| dim_t: 512 | |
| num_overlap: 2 |