model_mel_band_roformer_ep_3005_sdr_11.4360.yaml

audio:
  chunk_size: 352800
  dim_f: 1024
  dim_t: 801 # don't work (use in model)
  hop_length: 441 # don't work (use in model)
  n_fft: 2048
  num_channels: 2
  sample_rate: 44100
  min_mean_abs: 0.001

model:
  dim: 384
  depth: 12
  stereo: true
  num_stems: 1
  time_transformer_depth: 1
  freq_transformer_depth: 1
  num_bands: 60
  dim_head: 64
  heads: 8
  attn_dropout: 0.1
  ff_dropout: 0.1
  flash_attn: True
  dim_freqs_in: 1025
  sample_rate: 44100  # needed for mel filter bank from librosa
  stft_n_fft: 2048
  stft_hop_length: 441
  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

training:
  batch_size: 9
  gradient_accumulation_steps: 8
  grad_clip: 0
  instruments:
  - Vocals
  - Instrumental
  lr: 4.0e-05
  patience: 2
  reduce_factor: 0.95
  target_instrument: Vocals
  num_epochs: 1000
  num_steps: 1000
  augmentation: false # enable augmentations by audiomentations and pedalboard
  augmentation_type: simple1
  use_mp3_compress: false # Deprecated
  augmentation_mix: true # Mix several stems of the same type with some probability
  augmentation_loudness: true # randomly change loudness of each stem
  augmentation_loudness_type: 1 # Type 1 or 2
  augmentation_loudness_min: 0.5
  augmentation_loudness_max: 1.5
  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

inference:
  batch_size: 1
  dim_t: 801
  num_overlap: 4