config_vocals_mdx23c.yaml

audio:
  chunk_size: 261120
  dim_f: 4096
  dim_t: 256
  hop_length: 1024
  n_fft: 8192
  num_channels: 2
  sample_rate: 44100
  min_mean_abs: 0.001

model:
  act: gelu
  bottleneck_factor: 4
  growth: 128
  norm: InstanceNorm
  num_blocks_per_scale: 2
  num_channels: 128
  num_scales: 5
  num_subbands: 4
  scale:
  - 2
  - 2

training:
  batch_size: 2
  gradient_accumulation_steps: 1
  grad_clip: 0
  instruments:
  - vocals
  - other
  lr: 1.0e-05
  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: adam
  read_metadata_procs: 8 # Number of processes to use during metadata reading for dataset. Can speed up metadata generation
  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

  # apply mp3 compression to mixture only (emulate downloading mp3 from internet)
  mp3_compression_on_mixture: 0.01
  mp3_compression_on_mixture_bitrate_min: 32
  mp3_compression_on_mixture_bitrate_max: 320
  mp3_compression_on_mixture_backend: "lameenc"

  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)
    mp3_compression: 0.01
    mp3_compression_min_bitrate: 32
    mp3_compression_max_bitrate: 320
    mp3_compression_backend: "lameenc"

  vocals:
    pitch_shift: 0.1
    pitch_shift_min_semitones: -5
    pitch_shift_max_semitones: 5
    seven_band_parametric_eq: 0.25
    seven_band_parametric_eq_min_gain_db: -9
    seven_band_parametric_eq_max_gain_db: 9
    tanh_distortion: 0.1
    tanh_distortion_min: 0.1
    tanh_distortion_max: 0.7
  other:
    pitch_shift: 0.1
    pitch_shift_min_semitones: -4
    pitch_shift_max_semitones: 4
    gaussian_noise: 0.1
    gaussian_noise_min_amplitude: 0.001
    gaussian_noise_max_amplitude: 0.015
    time_stretch: 0.01
    time_stretch_min_rate: 0.8
    time_stretch_max_rate: 1.25

inference:
  batch_size: 1
  dim_t: 256
  num_overlap: 4