Upload 7 files
Browse files- Roformer_models/bs_roformer_male_female_by_aufr33_sdr_7.2889.ckpt +3 -0
- Roformer_models/config_mel_band_roformer_vocals_fullness_aname.yaml +54 -0
- Roformer_models/mel_band_roformer_inst_fullness_v7_gabox.ckpt +3 -0
- Roformer_models/mel_band_roformer_inst_fullness_v7_noise_gabox.ckpt +3 -0
- Roformer_models/mel_band_roformer_inst_fullness_vX_gabox.ckpt +3 -0
- Roformer_models/mel_band_roformer_karaoke_gabox.ckpt +3 -0
- Roformer_models/mel_band_roformer_vocals_fullness_aname.ckpt +3 -0
Roformer_models/bs_roformer_male_female_by_aufr33_sdr_7.2889.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf11736d1b42a11ae55d8299316585921477dd2a671b24b663660846ca9861b
|
| 3 |
+
size 527119779
|
Roformer_models/config_mel_band_roformer_vocals_fullness_aname.yaml
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
audio:
|
| 2 |
+
chunk_size: 661500
|
| 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: 0.001
|
| 10 |
+
|
| 11 |
+
model:
|
| 12 |
+
dim: 384
|
| 13 |
+
depth: 6
|
| 14 |
+
stereo: true
|
| 15 |
+
num_stems: 1
|
| 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
|
| 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 |
+
- other
|
| 48 |
+
target_instrument: vocals
|
| 49 |
+
use_amp: true
|
| 50 |
+
|
| 51 |
+
inference:
|
| 52 |
+
batch_size: 4
|
| 53 |
+
dim_t: 1101
|
| 54 |
+
num_overlap: 4
|
Roformer_models/mel_band_roformer_inst_fullness_v7_gabox.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e725a860176acb475d983a1ddd9c1a99a619c69cc9ceda808dd294d10db746a5
|
| 3 |
+
size 913026650
|
Roformer_models/mel_band_roformer_inst_fullness_v7_noise_gabox.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0ca36af5d1314be46b56c8a53b6be02f98511fa5d7e3e196fd895755e65be3c
|
| 3 |
+
size 913026650
|
Roformer_models/mel_band_roformer_inst_fullness_vX_gabox.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:545ef13b0cdbac505818a38db98e09c54e7c03ea17b4e0c895a531bfa352fa59
|
| 3 |
+
size 913026650
|
Roformer_models/mel_band_roformer_karaoke_gabox.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:303fc631e7aa587e9dc1e6ac4bb3667c6ba53aacb6b6a90abcfcf57935b92bd8
|
| 3 |
+
size 913026650
|
Roformer_models/mel_band_roformer_vocals_fullness_aname.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a64a27a672b457de23d9decd1fc7b58b0664a9f4f24bb43af154708e2ef07d2f
|
| 3 |
+
size 913090472
|