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: 0.001

model:
  encoder_name: tu-maxvit_large_tf_512 # look here for possibilities: https://github.com/qubvel/segmentation_models.pytorch#encoders-
  decoder_type: unet # unet, fpn
  act: gelu
  num_channels: 128
  num_subbands: 8

loss_multistft:
  fft_sizes:
  - 1024
  - 2048
  - 4096
  hop_sizes:
  - 512
  - 1024
  - 2048
  win_lengths:
  - 1024
  - 2048
  - 4096
  window: "hann_window"
  scale: "mel"
  n_bins: 128
  sample_rate: 44100
  perceptual_weighting: true
  w_sc: 1.0
  w_log_mag: 1.0
  w_lin_mag: 0.0
  w_phs: 0.0
  mag_distance: "L1"


training:
  batch_size: 8
  gradient_accumulation_steps: 1
  grad_clip: 0
  instruments:
  - vocals
  - other
  lr: 5.0e-05
  patience: 2
  reduce_factor: 0.95
  target_instrument: null
  num_epochs: 1000
  num_steps: 2000
  q: 0.95
  coarse_loss_clip: true
  ema_momentum: 0.999
  optimizer: adamw
  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: 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
  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

inference:
  batch_size: 1
  dim_t: 512
  num_overlap: 4