|
audio:
|
|
chunk_size: 485100
|
|
dim_f: 1024
|
|
dim_t: 801
|
|
hop_length: 441
|
|
n_fft: 2048
|
|
num_channels: 2
|
|
sample_rate: 44100
|
|
min_mean_abs: 0.000
|
|
|
|
model:
|
|
dim: 384
|
|
depth: 12
|
|
stereo: true
|
|
num_stems: 1
|
|
time_transformer_depth: 1
|
|
freq_transformer_depth: 1
|
|
freqs_per_bands: !!python/tuple
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 2
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 4
|
|
- 12
|
|
- 12
|
|
- 12
|
|
- 12
|
|
- 12
|
|
- 12
|
|
- 12
|
|
- 12
|
|
- 24
|
|
- 24
|
|
- 24
|
|
- 24
|
|
- 24
|
|
- 24
|
|
- 24
|
|
- 24
|
|
- 48
|
|
- 48
|
|
- 48
|
|
- 48
|
|
- 48
|
|
- 48
|
|
- 48
|
|
- 48
|
|
- 128
|
|
- 129
|
|
dim_head: 64
|
|
heads: 8
|
|
attn_dropout: 0
|
|
ff_dropout: 0
|
|
flash_attn: true
|
|
dim_freqs_in: 1025
|
|
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: 1
|
|
gradient_accumulation_steps: 1
|
|
grad_clip: 0
|
|
instruments:
|
|
- vocals
|
|
- other
|
|
lr: 1.0e-04
|
|
patience: 2
|
|
reduce_factor: 0.95
|
|
target_instrument: other
|
|
num_epochs: 1
|
|
num_steps: 1000
|
|
q: 0.95
|
|
coarse_loss_clip: true
|
|
ema_momentum: 0.999
|
|
optimizer: adamw
|
|
other_fix: true
|
|
use_amp: true
|
|
|
|
inference:
|
|
batch_size: 1
|
|
dim_t: 1101
|
|
num_overlap: 2 |
