Cool_Tools/ultimatevocalremovergui
1
0
Fork 0
mirror of https://github.com/Anjok07/ultimatevocalremovergui.git synced 2024-11-27 17:00:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Anjok07 2023-09-25 17:14:57 -05:00 committed by GitHub
parent db9cf7b94f
commit eb1ee99c96
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
17 changed files with 649 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
models/MDX_Net_Models/desktop.ini Normal file
View File

@ -0,0 +1,9 @@
[LocalizedFileNames]
UVR-MDX-NET_Main_439.onnx=@UVR-MDX-NET_Main_439.onnx,0
UVR-MDX-NET_Main_438.onnx=@UVR-MDX-NET_Main_438.onnx,0
UVR-MDX-NET_Main_437.onnx=@UVR-MDX-NET_Main_437.onnx,0
UVR-MDX-NET_Main_436.onnx=@UVR-MDX-NET_Main_436.onnx,0
UVR-MDX-NET_Main_435.onnx=@UVR-MDX-NET_Main_435.onnx,0
UVR-MDX-NET_Main_434.onnx=@UVR-MDX-NET_Main_434.onnx,0
bass.onnx=@bass.onnx,0
drums.onnx=@drums.onnx,0

34
models/MDX_Net_Models/model_data/mdx_c_configs/model1.yaml Normal file
View File

@ -0,0 +1,34 @@
audio:
chunk_size: 260096
dim_f: 4096
dim_t: 128
hop_length: 2048
n_fft: 8192
num_channels: 2
sample_rate: 44100
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
training:
batch_size: 8
grad_clip: 0
instruments:
- Vocals
- Drums
- Bass
- Other
lr: 5.0e-05
target_instrument: null
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

34
models/MDX_Net_Models/model_data/mdx_c_configs/model2.yaml Normal file
View File

@ -0,0 +1,34 @@
audio:
chunk_size: 260096
dim_f: 4096
dim_t: 128
hop_length: 2048
n_fft: 8192
num_channels: 2
sample_rate: 44100
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 256
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
training:
batch_size: 8
grad_clip: 0
instruments:
- Vocals
- Drums
- Bass
- Other
lr: 3.0e-05
target_instrument: null
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

34
models/MDX_Net_Models/model_data/mdx_c_configs/model3.yaml Normal file
View File

@ -0,0 +1,34 @@
audio:
chunk_size: 260096
dim_f: 4096
dim_t: 128
hop_length: 2048
n_fft: 12288
num_channels: 2
sample_rate: 44100
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
training:
batch_size: 8
grad_clip: 0
instruments:
- Vocals
- Drums
- Bass
- Other
lr: 5.0e-05
target_instrument: Vocals
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

39
models/MDX_Net_Models/model_data/mdx_c_configs/modelA.yaml Normal file
View File

@ -0,0 +1,39 @@
audio:
chunk_size: 261120
dim_f: 4096
dim_t: 256
hop_length: 1024
min_mean_abs: 0.01
n_fft: 8192
num_channels: 2
sample_rate: 44100
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 64
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
training:
batch_size: 6
coarse_loss_clip: true
ema_momentum: 0.999
grad_clip: null
instruments:
- Vocals
- Drums
- Bass
- Other
lr: 0.0001
num_steps: 100000
q: 0.4
target_instrument: null
inference:
batch_size: 2
dim_t: 256
num_overlap: 8

41
models/MDX_Net_Models/model_data/mdx_c_configs/modelB.yaml Normal file
View File

@ -0,0 +1,41 @@
audio:
chunk_size: 261120
dim_f: 4096
dim_t: 256
hop_length: 1024
min_mean_abs: 0.01
n_fft: 8192
num_channels: 2
sample_rate: 44100
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 64
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
training:
batch_size: 6
coarse_loss_clip: false
datasets:
- ../data/moises/bleeding
ema_momentum: 0.999
grad_clip: null
instruments:
- Vocals
- Drums
- Bass
- Other
lr: 0.0001
num_steps: 150000
q: 0.93
target_instrument: null
inference:
batch_size: 2
dim_t: 256
num_overlap: 8

36
models/MDX_Net_Models/model_data/mdx_c_configs/model_2_stem_061321.yaml Normal file
View File

@ -0,0 +1,36 @@
audio:
chunk_size: 260096
dim_f: 4096
dim_t: 256
hop_length: 2048
n_fft: 12288
num_channels: 2
sample_rate: 44100
min_mean_abs: 0.001
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
name: epoch_10.ckpt
training:
batch_size: 16
grad_clip: 0
instruments:
- Vocals
- Instrumental
lr: 5.0e-05
target_instrument: null
num_epochs: 100
num_steps: 1000
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

36
models/MDX_Net_Models/model_data/mdx_c_configs/model_2_stem_full_band.yaml Normal file
View File

@ -0,0 +1,36 @@
audio:
chunk_size: 260096
dim_f: 6144
dim_t: 128
hop_length: 2048
n_fft: 12288
num_channels: 2
sample_rate: 44100
min_mean_abs: 0.001
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 6
scale:
- 2
- 2
training:
batch_size: 14
grad_clip: 0
instruments:
- Vocals
- Instrumental
lr: 3.0e-05
target_instrument: null
num_epochs: 1000
num_steps: 1000
augmentation: 1
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

36
models/MDX_Net_Models/model_data/mdx_c_configs/model_2_stem_full_band_2.yaml Normal file
View File

@ -0,0 +1,36 @@
audio:
chunk_size: 260096
dim_f: 6144
dim_t: 128
hop_length: 2048
n_fft: 12288
num_channels: 2
sample_rate: 44100
min_mean_abs: 0.001
model:
act: gelu
bottleneck_factor: 4
growth: 128
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 6
scale:
- 2
- 2
training:
batch_size: 14
grad_clip: 0
instruments:
- Vocals
- Instrumental
lr: 2.0e-05
target_instrument: null
num_epochs: 1000
num_steps: 1000
augmentation: 1
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

39
models/MDX_Net_Models/model_data/mdx_c_configs/model_2_stem_full_band_3.yaml Normal file
View File

@ -0,0 +1,39 @@
audio:
chunk_size: 261120
dim_f: 6144
dim_t: 256
hop_length: 1024
n_fft: 12288
num_channels: 2
sample_rate: 44100
min_mean_abs: 0.001
model:
act: gelu
bottleneck_factor: 4
growth: 128
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 6
scale:
- 2
- 2
training:
batch_size: 6
grad_clip: 0
instruments:
- Vocals
- Instrumental
lr: 1.0e-05
target_instrument: null
num_epochs: 1000
num_steps: 1000
augmentation: 1
q: 0.95
coarse_loss_clip: true
ema_momentum: 0.999
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

40
models/MDX_Net_Models/model_data/mdx_c_configs/model_2_stem_full_band_4.yaml Normal file
View File

@ -0,0 +1,40 @@
audio:
chunk_size: 261120
dim_f: 6144
dim_t: 256
hop_length: 1024
n_fft: 12288
num_channels: 2
sample_rate: 44100
min_mean_abs: 0.001
model:
act: gelu
bottleneck_factor: 4
growth: 128
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 6
scale:
- 2
- 2
training:
batch_size: 6
grad_clip: 0
instruments:
- Vocals
- Instrumental
lr: 0.7e-05
patience: 2
target_instrument: null
num_epochs: 1000
num_steps: 1000
augmentation: 1
q: 0.95
coarse_loss_clip: true
ema_momentum: 0.999
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

43
models/MDX_Net_Models/model_data/mdx_c_configs/model_2_stem_full_band_8k.yaml Normal file
View File

@ -0,0 +1,43 @@
audio:
chunk_size: 261120
dim_f: 4096
dim_t: 256
hop_length: 1024
n_fft: 8192
num_channels: 2
sample_rate: 44100
min_mean_abs: 0.001
model:
act: gelu
bottleneck_factor: 4
growth: 128
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 128
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
training:
batch_size: 6
grad_clip: 0
instruments:
- Vocals
- Instrumental
lr: 1.0e-05
patience: 2
reduce_factor: 0.95
target_instrument: null
num_epochs: 1000
num_steps: 1000
augmentation: 1
augmentation_type: simple1
augmentation_mix: true
q: 0.95
coarse_loss_clip: true
ema_momentum: 0.999
inference:
batch_size: 1
dim_t: 256
num_overlap: 8

41
models/MDX_Net_Models/model_data/mdx_c_configs/sndfx.yaml Normal file
View File

@ -0,0 +1,41 @@
audio:
chunk_size: 261120
dim_f: 1024
dim_t: 256
hop_length: 1024
min_mean_abs: 0.01
n_fft: 2048
num_channels: 2
sample_rate: 44100
stereo_prob: 0.7
model:
act: gelu
bottleneck_factor: 4
growth: 64
norm: InstanceNorm
num_blocks_per_scale: 2
num_channels: 64
num_scales: 5
num_subbands: 4
scale:
- 2
- 2
training:
batch_size: 8
ema_momentum: 0.999
grad_clip: null
instruments:
- Music
- Speech
- SFX
lr: 0.0001
num_steps: 30000
target_instrument: null
inference:
batch_size: 8
dim_t: 256
instruments:
- Music
- Dialog
- Effect
num_overlap: 8

144
models/MDX_Net_Models/model_data/model_data.json
View File

@ -14,7 +14,7 @@
"primary_stem": "Other"
},
"2cdd429caac38f0194b133884160f2c6": {
"compensate": 1.035,
"compensate": 1.045,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
@ -25,7 +25,8 @@
"mdx_dim_f_set": 2048,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 6144,
"primary_stem": "Vocals"
"primary_stem": "Vocals",
"is_karaoke": true
},
"398580b6d5d973af3120df54cee6759d": {
"compensate": 1.75,
@ -49,7 +50,7 @@
"primary_stem": "Drums"
},
"53c4baf4d12c3e6c3831bb8f5b532b93": {
"compensate": 1.035,
"compensate": 1.043,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
@ -91,21 +92,21 @@
"primary_stem": "Vocals"
},
"867595e9de46f6ab699008295df62798": {
"compensate": 1.075,
"compensate": 1.03,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Vocals"
},
"a3cd63058945e777505c01d2507daf37": {
"compensate": 1.035,
"compensate": 1.03,
"mdx_dim_f_set": 2048,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 6144,
"primary_stem": "Vocals"
},
"b33d9b3950b6cbf5fe90a32608924700": {
"compensate": 1.075,
"compensate": 1.03,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
@ -154,21 +155,21 @@
"primary_stem": "Drums"
},
"e5572e58abf111f80d8241d2e44e7fa4": {
"compensate": 1.035,
"compensate": 1.028,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Instrumental"
},
"e7324c873b1f615c35c1967f912db92a": {
"compensate": 1.075,
"compensate": 1.03,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Vocals"
},
"1c56ec0224f1d559c42fd6fd2a67b154": {
"compensate": 1.035,
"compensate": 1.025,
"mdx_dim_f_set": 2048,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 5120,
@ -189,25 +190,33 @@
"primary_stem": "Instrumental"
},
"94ff780b977d3ca07c7a343dab2e25dd": {
"compensate": 1.035,
"compensate": 1.039,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 6144,
"primary_stem": "Instrumental"
},
"73492b58195c3b52d34590d5474452f6": {
"compensate": 1.075,
"compensate": 1.043,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Vocals"
},
"970b3f9492014d18fefeedfe4773cb42": {
"compensate": 1.009,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Vocals"
},
"1d64a6d2c30f709b8c9b4ce1366d96ee": {
"compensate": 1.035,
"compensate": 1.065,
"mdx_dim_f_set": 2048,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 5120,
"primary_stem": "Instrumental"
"primary_stem": "Instrumental",
"is_karaoke": true
},
"203f2a3955221b64df85a41af87cf8f0": {
"compensate": 1.035,
@ -229,5 +238,114 @@
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 6144,
"primary_stem": "Instrumental"
},
"cc63408db3d80b4d85b0287d1d7c9632": {
"compensate": 1.033,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 6144,
"primary_stem": "Instrumental"
},
"cd5b2989ad863f116c855db1dfe24e39": {
"compensate": 1.035,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 9,
"mdx_n_fft_scale_set": 6144,
"primary_stem": "Reverb"
},
"55657dd70583b0fedfba5f67df11d711": {
"compensate": 1.022,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 6144,
"primary_stem": "Instrumental"
},
"b6bccda408a436db8500083ef3491e8b": {
"compensate": 1.02,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Instrumental"
},
"8a88db95c7fb5dbe6a095ff2ffb428b1": {
"compensate": 1.026,
"mdx_dim_f_set": 2048,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 5120,
"primary_stem": "Instrumental"
},
"b78da4afc6512f98e4756f5977f5c6b9": {
"compensate": 1.021,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Instrumental"
},
"77d07b2667ddf05b9e3175941b4454a0": {
"compensate": 1.021,
"mdx_dim_f_set": 3072,
"mdx_dim_t_set": 8,
"mdx_n_fft_scale_set": 7680,
"primary_stem": "Vocals"
},
"2154254ee89b2945b97a7efed6e88820": {
"config_yaml": "model_2_stem_061321.yaml"
},
"063aadd735d58150722926dcbf5852a9": {
"config_yaml": "model_2_stem_061321.yaml"
},
"c09f714d978b41d718facfe3427e6001": {
"config_yaml": "model_2_stem_061321.yaml"
},
"fe96801369f6a148df2720f5ced88c19": {
"config_yaml": "model3.yaml"
},
"02e8b226f85fb566e5db894b9931c640": {
"config_yaml": "model2.yaml"
},
"e3de6d861635ab9c1d766149edd680d6": {
"config_yaml": "model1.yaml"
},
"3f2936c554ab73ce2e396d54636bd373": {
"config_yaml": "modelB.yaml"
},
"890d0f6f82d7574bca741a9e8bcb8168": {
"config_yaml": "modelB.yaml"
},
"63a3cb8c37c474681049be4ad1ba8815": {
"config_yaml": "modelB.yaml"
},
"a7fc5d719743c7fd6b61bd2b4d48b9f0": {
"config_yaml": "modelA.yaml"
},
"3567f3dee6e77bf366fcb1c7b8bc3745": {
"config_yaml": "modelA.yaml"
},
"a28f4d717bd0d34cd2ff7a3b0a3d065e": {
"config_yaml": "modelA.yaml"
},
"c9971a18da20911822593dc81caa8be9": {
"config_yaml": "sndfx.yaml"
},
"57d94d5ed705460d21c75a5ac829a605": {
"config_yaml": "sndfx.yaml"
},
"e7a25f8764f25a52c1b96c4946e66ba2": {
"config_yaml": "sndfx.yaml"
},
"104081d24e37217086ce5fde09147ee1": {
"config_yaml": "model_2_stem_061321.yaml"
},
"1e6165b601539f38d0a9330f3facffeb": {
"config_yaml": "model_2_stem_061321.yaml"
},
"fe0108464ce0d8271be5ab810891bd7c": {
"config_yaml": "model_2_stem_full_band.yaml"
},
"e9b82ec90ee56c507a3a982f1555714c": {
"config_yaml": "model_2_stem_full_band_2.yaml"
},
"99b6ceaae542265a3b6d657bf9fde79f": {
"config_yaml": "model_2_stem_full_band_8k.yaml"
}
}

11
models/MDX_Net_Models/model_data/model_name_mapper.json
View File

@ -7,7 +7,16 @@
"UVR-MDX-NET-Inst_1": "UVR-MDX-NET Inst 1",
"UVR-MDX-NET-Inst_2": "UVR-MDX-NET Inst 2",
"UVR-MDX-NET-Inst_3": "UVR-MDX-NET Inst 3",
"UVR-MDX-NET-Inst_4": "UVR-MDX-NET Inst 4",
"UVR-MDX-NET-Inst_Main": "UVR-MDX-NET Inst Main",
"UVR-MDX-NET-Inst_Main_2": "UVR-MDX-NET Inst Main 2",
"UVR-MDX-NET-Inst_HQ_1": "UVR-MDX-NET Inst HQ 1",
"UVR_MDXNET_KARA_2": "UVR-MDX-NET Karaoke 2"
"UVR-MDX-NET-Inst_HQ_2": "UVR-MDX-NET Inst HQ 2",
"UVR-MDX-NET-Inst_HQ_3": "UVR-MDX-NET Inst HQ 3",
"UVR_MDXNET_KARA_2": "UVR-MDX-NET Karaoke 2",
"Kim_Vocal_1": "Kim Vocal 1",
"Kim_Vocal_2": "Kim Vocal 2",
"Kim_Inst": "Kim Inst",
"MDX23C-8KFFT-InstVoc_HQ.ckpt": "MDX23C-InstVoc HQ",
"Reverb_HQ_By_FoxJoy": "Reverb HQ"
}

BIN
models/VR_Models/UVR-DeNoise-Lite.pth Normal file
View File

Binary file not shown.

49
models/VR_Models/model_data/model_data.json
View File

@ -13,7 +13,7 @@
},
"2aa34fbc01f8e6d2bf509726481e7142": {
"vr_model_param": "4band_44100",
"primary_stem": "Other"
"primary_stem": "No Piano"
},
"3e18f639b11abea7361db1a4a91c2559": {
"vr_model_param": "4band_44100",
@ -29,7 +29,8 @@
},
"6b5916069a49be3fe29d4397ecfd73fa": {
"vr_model_param": "3band_44100_msb2",
"primary_stem": "Instrumental"
"primary_stem": "Instrumental",
"is_karaoke": true
},
"74b3bc5fa2b69f29baf7839b858bc679": {
"vr_model_param": "4band_44100",
@ -85,10 +86,52 @@
},
"f6ea8473ff86017b5ebd586ccacf156b": {
"vr_model_param": "4band_v2_sn",
"primary_stem": "Instrumental"
"primary_stem": "Instrumental",
"is_karaoke": true
},
"fd297a61eafc9d829033f8b987c39a3d": {
"vr_model_param": "1band_sr32000_hl512",
"primary_stem": "Instrumental"
},
"0ec76fd9e65f81d8b4fbd13af4826ed8": {
"vr_model_param": "4band_v3",
"primary_stem": "No Woodwinds"
},
"0fb9249ffe4ffc38d7b16243f394c0ff": {
"vr_model_param": "4band_v3",
"primary_stem": "No Reverb"
},
"6857b2972e1754913aad0c9a1678c753": {
"vr_model_param": "4band_v3",
"primary_stem": "Echo",
"nout": 48,
"nout_lstm": 128
},
"f200a145434efc7dcf0cd093f517ed52": {
"vr_model_param": "4band_v3",
"primary_stem": "No Echo",
"nout": 48,
"nout_lstm": 128
},
"44c55d8b5d2e3edea98c2b2bf93071c7": {
"vr_model_param": "4band_v3",
"primary_stem": "Noise",
"nout": 48,
"nout_lstm": 128
},
"51ea8c43a6928ed3c10ef5cb2707d57b": {
"vr_model_param": "1band_sr44100_hl1024",
"primary_stem": "Noise",
"nout": 16,
"nout_lstm": 128
},
"944950a9c5963a5eb70b445d67b7068a": {
"vr_model_param": "4band_v3_sn",
"primary_stem": "Vocals",
"nout": 64,
"nout_lstm": 128,
"is_karaoke": false,
"is_bv_model": true,
"is_bv_model_rebalanced": 0.9
}
}