Upload 2 files
Browse files
models/Roformer/MelBand/config_melband_roformer_karaoke_becruily.yaml
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
audio:
|
| 2 |
+
chunk_size: 485100
|
| 3 |
+
dim_f: 1024
|
| 4 |
+
dim_t: 256
|
| 5 |
+
hop_length: 441
|
| 6 |
+
n_fft: 2048
|
| 7 |
+
num_channels: 2
|
| 8 |
+
sample_rate: 44100
|
| 9 |
+
min_mean_abs: 0.000
|
| 10 |
+
|
| 11 |
+
model:
|
| 12 |
+
dim: 384
|
| 13 |
+
depth: 6
|
| 14 |
+
stereo: true
|
| 15 |
+
num_stems: 2
|
| 16 |
+
time_transformer_depth: 1
|
| 17 |
+
freq_transformer_depth: 1
|
| 18 |
+
num_bands: 60
|
| 19 |
+
dim_head: 64
|
| 20 |
+
heads: 8
|
| 21 |
+
attn_dropout: 0
|
| 22 |
+
ff_dropout: 0
|
| 23 |
+
flash_attn: true
|
| 24 |
+
dim_freqs_in: 1025
|
| 25 |
+
sample_rate: 44100 # needed for mel filter bank from librosa
|
| 26 |
+
stft_n_fft: 2048
|
| 27 |
+
stft_hop_length: 441
|
| 28 |
+
stft_win_length: 2048
|
| 29 |
+
stft_normalized: false
|
| 30 |
+
mask_estimator_depth: 2
|
| 31 |
+
multi_stft_resolution_loss_weight: 1.0
|
| 32 |
+
multi_stft_resolutions_window_sizes: !!python/tuple
|
| 33 |
+
- 4096
|
| 34 |
+
- 2048
|
| 35 |
+
- 1024
|
| 36 |
+
- 512
|
| 37 |
+
- 256
|
| 38 |
+
multi_stft_hop_size: 147
|
| 39 |
+
multi_stft_normalized: false
|
| 40 |
+
|
| 41 |
+
training:
|
| 42 |
+
batch_size: 1
|
| 43 |
+
gradient_accumulation_steps: 1
|
| 44 |
+
grad_clip: 0
|
| 45 |
+
instruments:
|
| 46 |
+
- Vocals
|
| 47 |
+
- Instrumental
|
| 48 |
+
lr: 0.0005
|
| 49 |
+
patience: 2
|
| 50 |
+
reduce_factor: 0.95
|
| 51 |
+
target_instrument: null
|
| 52 |
+
num_epochs: 1000
|
| 53 |
+
num_steps: 1000
|
| 54 |
+
augmentation: false # enable augmentations by audiomentations and pedalboard
|
| 55 |
+
augmentation_type:
|
| 56 |
+
use_mp3_compress: false # Deprecated
|
| 57 |
+
augmentation_mix: false # Mix several stems of the same type with some probability
|
| 58 |
+
augmentation_loudness: false # randomly change loudness of each stem
|
| 59 |
+
augmentation_loudness_type: 1 # Type 1 or 2
|
| 60 |
+
augmentation_loudness_min: 0
|
| 61 |
+
augmentation_loudness_max: 0
|
| 62 |
+
q: 0.95
|
| 63 |
+
coarse_loss_clip: false
|
| 64 |
+
ema_momentum: 0.999
|
| 65 |
+
optimizer: adamw
|
| 66 |
+
other_fix: false # it's needed for checking on multisong dataset if other is actually instrumental
|
| 67 |
+
use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
|
| 68 |
+
|
| 69 |
+
inference:
|
| 70 |
+
batch_size: 1
|
| 71 |
+
dim_t: 1101
|
| 72 |
+
num_overlap: 8
|
models/Roformer/MelBand/melband_roformer_karaoke_becruily.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3aa262ac01df870b9fc033e9c7b6cad33fe04fc9c148b6c40841326a515a0e0
|
| 3 |
+
size 1719139254
|