config_apollo_vocal.yaml

audio:
  chunk_size: 132300
  num_channels: 2
  sample_rate: 44100
  min_mean_abs: 0.0

model:
  sr: 44100
  win: 20
  feature_dim: 192
  layer: 6

training:
  instruments: ['restored', 'addition']
  target_instrument: 'restored'
  batch_size: 1
  gradient_accumulation_steps: 2
  num_steps: 1000
  num_epochs: 1000
  optimizer: 'prodigy'
  lr:  1.0
  patience: 2
  reduce_factor: 0.95
  coarse_loss_clip: true
  grad_clip: 0
  q: 0.95
  use_amp: false

optimizer:
  weight_decay: 0.01
  betas: [0.5, 0.99]

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

inference:
  batch_size: 1
  num_overlap: 4