Upload 2 files
Browse files
model_bs_roformer_ep_0_sdr_12.3922.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f4af693f8fd546f218f2df63514e063479ff29e445f21e54f79c33685d64d47
|
| 3 |
+
size 639330302
|
model_bs_roformer_vocals.yaml
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
audio:
|
| 2 |
+
chunk_size: 352800
|
| 3 |
+
dim_f: 1024
|
| 4 |
+
dim_t: 801 # don't work (use in model)
|
| 5 |
+
hop_length: 441 # don't work (use in model)
|
| 6 |
+
n_fft: 2048
|
| 7 |
+
num_channels: 2
|
| 8 |
+
sample_rate: 44100
|
| 9 |
+
min_mean_abs: 0.000
|
| 10 |
+
|
| 11 |
+
model:
|
| 12 |
+
dim: 512
|
| 13 |
+
depth: 12
|
| 14 |
+
stereo: true
|
| 15 |
+
num_stems: 1
|
| 16 |
+
time_transformer_depth: 1
|
| 17 |
+
freq_transformer_depth: 1
|
| 18 |
+
linear_transformer_depth: 0
|
| 19 |
+
freqs_per_bands: !!python/tuple
|
| 20 |
+
- 2
|
| 21 |
+
- 2
|
| 22 |
+
- 2
|
| 23 |
+
- 2
|
| 24 |
+
- 2
|
| 25 |
+
- 2
|
| 26 |
+
- 2
|
| 27 |
+
- 2
|
| 28 |
+
- 2
|
| 29 |
+
- 2
|
| 30 |
+
- 2
|
| 31 |
+
- 2
|
| 32 |
+
- 2
|
| 33 |
+
- 2
|
| 34 |
+
- 2
|
| 35 |
+
- 2
|
| 36 |
+
- 2
|
| 37 |
+
- 2
|
| 38 |
+
- 2
|
| 39 |
+
- 2
|
| 40 |
+
- 2
|
| 41 |
+
- 2
|
| 42 |
+
- 2
|
| 43 |
+
- 2
|
| 44 |
+
- 4
|
| 45 |
+
- 4
|
| 46 |
+
- 4
|
| 47 |
+
- 4
|
| 48 |
+
- 4
|
| 49 |
+
- 4
|
| 50 |
+
- 4
|
| 51 |
+
- 4
|
| 52 |
+
- 4
|
| 53 |
+
- 4
|
| 54 |
+
- 4
|
| 55 |
+
- 4
|
| 56 |
+
- 12
|
| 57 |
+
- 12
|
| 58 |
+
- 12
|
| 59 |
+
- 12
|
| 60 |
+
- 12
|
| 61 |
+
- 12
|
| 62 |
+
- 12
|
| 63 |
+
- 12
|
| 64 |
+
- 24
|
| 65 |
+
- 24
|
| 66 |
+
- 24
|
| 67 |
+
- 24
|
| 68 |
+
- 24
|
| 69 |
+
- 24
|
| 70 |
+
- 24
|
| 71 |
+
- 24
|
| 72 |
+
- 48
|
| 73 |
+
- 48
|
| 74 |
+
- 48
|
| 75 |
+
- 48
|
| 76 |
+
- 48
|
| 77 |
+
- 48
|
| 78 |
+
- 48
|
| 79 |
+
- 48
|
| 80 |
+
- 128
|
| 81 |
+
- 129
|
| 82 |
+
dim_head: 64
|
| 83 |
+
heads: 8
|
| 84 |
+
attn_dropout: 0.1
|
| 85 |
+
ff_dropout: 0.1
|
| 86 |
+
flash_attn: true
|
| 87 |
+
dim_freqs_in: 1025
|
| 88 |
+
stft_n_fft: 2048
|
| 89 |
+
stft_hop_length: 441
|
| 90 |
+
stft_win_length: 2048
|
| 91 |
+
stft_normalized: false
|
| 92 |
+
mask_estimator_depth: 2
|
| 93 |
+
multi_stft_resolution_loss_weight: 1.0
|
| 94 |
+
multi_stft_resolutions_window_sizes: !!python/tuple
|
| 95 |
+
- 4096
|
| 96 |
+
- 2048
|
| 97 |
+
- 1024
|
| 98 |
+
- 512
|
| 99 |
+
- 256
|
| 100 |
+
multi_stft_hop_size: 147
|
| 101 |
+
multi_stft_normalized: False
|
| 102 |
+
|
| 103 |
+
training:
|
| 104 |
+
batch_size: 2
|
| 105 |
+
gradient_accumulation_steps: 1
|
| 106 |
+
grad_clip: 0
|
| 107 |
+
instruments:
|
| 108 |
+
- vocals
|
| 109 |
+
- other
|
| 110 |
+
lr: 1.0e-05
|
| 111 |
+
patience: 2
|
| 112 |
+
reduce_factor: 0.95
|
| 113 |
+
target_instrument: vocals
|
| 114 |
+
num_epochs: 1000
|
| 115 |
+
num_steps: 1000
|
| 116 |
+
q: 0.95
|
| 117 |
+
coarse_loss_clip: true
|
| 118 |
+
ema_momentum: 0.999
|
| 119 |
+
optimizer: adam
|
| 120 |
+
other_fix: true # it's needed for checking on multisong dataset if other is actually instrumental
|
| 121 |
+
use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
|
| 122 |
+
|
| 123 |
+
inference:
|
| 124 |
+
batch_size: 4
|
| 125 |
+
dim_t: 801
|
| 126 |
+
num_overlap: 2
|