File size: 1,279 Bytes
3978e51 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
audio:
chunk_size: 132300 # samplerate * segment
hop_length: 1024
min_mean_abs: 0.0
training:
batch_size: 8
gradient_accumulation_steps: 1
grad_clip: 0
segment: 11
shift: 1
samplerate: 44100
channels: 2
normalize: true
instruments: ['vocals', 'other']
target_instrument: null
num_epochs: 1000
num_steps: 1000
optimizer: prodigy
lr: 1.0
patience: 2
reduce_factor: 0.95
q: 0.95
coarse_loss_clip: true
ema_momentum: 0.999
read_metadata_procs: 8
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
model:
sr: 44100
win: 2048
stride: 512
feature_dim: 128
num_repeat_mask: 8
num_repeat_map: 4
num_output: 2
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: [0.2, 0.02]
mixup_loudness_min: 0.5
mixup_loudness_max: 1.5
inference:
num_overlap: 2
batch_size: 4 |