File size: 908 Bytes
4754d23 |
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: 485100
dim_f: 1024
dim_t: 1101
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
num_bands: 60
dim_head: 64
heads: 8
attn_dropout: 0
ff_dropout: 0
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: 3
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:
instruments:
- vocals
- other
target_instrument: vocals
use_amp: True
inference:
batch_size: 1
dim_t: 1101
num_overlap: 2 |