Hugging Face's logo

therealvul
/
so-vits-svc-3.0

English
Model card Files Community
1
therealvul commited on
Commit
e2d8329
•
1 Parent(s): c50a237

Upload 9 files

Browse files
Files changed (9) hide show
  1. Cadance (singing) 3.0/D_29000.pth +3 -0
  2. Cadance (singing) 3.0/G_29000.pth +3 -0
  3. Cadance (singing) 3.0/config.json +90 -0
  4. Rarity (singing, reduced dataset) 3.0/D_17000.pth +3 -0
  5. Rarity (singing, reduced dataset) 3.0/G_17000.pth +3 -0
  6. Rarity (singing, reduced dataset) 3.0/config.json +90 -0
  7. sovits_pinkie_32khz_34000/D_34000.pth +3 -0
  8. sovits_pinkie_32khz_34000/G_34000.pth +3 -0
  9. sovits_pinkie_32khz_34000/config.json +90 -0
Cadance (singing) 3.0/D_29000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313206fac6a75bf0285c8a4e54157472f4570f3943523c6233cd9185881f7506
3
+ size 561070567
Cadance (singing) 3.0/G_29000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b212c256906d6f0461591f9a3da740734e664b0570c0de32cb9ccd9971b0838d
3
+ size 699313500
Cadance (singing) 3.0/config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "eval_interval": 1000,
5
+ "seed": 1234,
6
+ "epochs": 10000,
7
+ "learning_rate": 0.0001,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 12,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 17920,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0,
21
+ "use_sr": true,
22
+ "max_speclen": 384,
23
+ "port": "8001"
24
+ },
25
+ "data": {
26
+ "training_files": "filelists/train.txt",
27
+ "validation_files": "filelists/val.txt",
28
+ "max_wav_value": 32768.0,
29
+ "sampling_rate": 32000,
30
+ "filter_length": 1280,
31
+ "hop_length": 320,
32
+ "win_length": 1280,
33
+ "n_mel_channels": 80,
34
+ "mel_fmin": 0.0,
35
+ "mel_fmax": null
36
+ },
37
+ "model": {
38
+ "inter_channels": 192,
39
+ "hidden_channels": 192,
40
+ "filter_channels": 768,
41
+ "n_heads": 2,
42
+ "n_layers": 6,
43
+ "kernel_size": 3,
44
+ "p_dropout": 0.1,
45
+ "resblock": "1",
46
+ "resblock_kernel_sizes": [
47
+ 3,
48
+ 7,
49
+ 11
50
+ ],
51
+ "resblock_dilation_sizes": [
52
+ [
53
+ 1,
54
+ 3,
55
+ 5
56
+ ],
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ]
67
+ ],
68
+ "upsample_rates": [
69
+ 10,
70
+ 8,
71
+ 2,
72
+ 2
73
+ ],
74
+ "upsample_initial_channel": 512,
75
+ "upsample_kernel_sizes": [
76
+ 16,
77
+ 16,
78
+ 4,
79
+ 4
80
+ ],
81
+ "n_layers_q": 3,
82
+ "use_spectral_norm": false,
83
+ "gin_channels": 256,
84
+ "ssl_dim": 256,
85
+ "n_speakers": 2
86
+ },
87
+ "spk": {
88
+ "Cadance": 0
89
+ }
90
+ }
Rarity (singing, reduced dataset) 3.0/D_17000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3552513b059561006d038f04798d2bd468f968bdcada940b217abe5ea4e3c765
3
+ size 561070567
Rarity (singing, reduced dataset) 3.0/G_17000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d952e04e9330af57dc6225e3c580ab6011c611c712dd9739a71b6247d2321e0
3
+ size 699313500
Rarity (singing, reduced dataset) 3.0/config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "eval_interval": 1000,
5
+ "seed": 1234,
6
+ "epochs": 10000,
7
+ "learning_rate": 0.0001,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 12,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 17920,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0,
21
+ "use_sr": true,
22
+ "max_speclen": 384,
23
+ "port": "8001"
24
+ },
25
+ "data": {
26
+ "training_files": "filelists/train.txt",
27
+ "validation_files": "filelists/val.txt",
28
+ "max_wav_value": 32768.0,
29
+ "sampling_rate": 32000,
30
+ "filter_length": 1280,
31
+ "hop_length": 320,
32
+ "win_length": 1280,
33
+ "n_mel_channels": 80,
34
+ "mel_fmin": 0.0,
35
+ "mel_fmax": null
36
+ },
37
+ "model": {
38
+ "inter_channels": 192,
39
+ "hidden_channels": 192,
40
+ "filter_channels": 768,
41
+ "n_heads": 2,
42
+ "n_layers": 6,
43
+ "kernel_size": 3,
44
+ "p_dropout": 0.1,
45
+ "resblock": "1",
46
+ "resblock_kernel_sizes": [
47
+ 3,
48
+ 7,
49
+ 11
50
+ ],
51
+ "resblock_dilation_sizes": [
52
+ [
53
+ 1,
54
+ 3,
55
+ 5
56
+ ],
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ]
67
+ ],
68
+ "upsample_rates": [
69
+ 10,
70
+ 8,
71
+ 2,
72
+ 2
73
+ ],
74
+ "upsample_initial_channel": 512,
75
+ "upsample_kernel_sizes": [
76
+ 16,
77
+ 16,
78
+ 4,
79
+ 4
80
+ ],
81
+ "n_layers_q": 3,
82
+ "use_spectral_norm": false,
83
+ "gin_channels": 256,
84
+ "ssl_dim": 256,
85
+ "n_speakers": 2
86
+ },
87
+ "spk": {
88
+ "Rarity (singing reduced)": 0
89
+ }
90
+ }
sovits_pinkie_32khz_34000/D_34000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a307af1386e193f1aa390a9f69a508e101ec95d104344c4bff29422297d5d7
3
+ size 561099401
sovits_pinkie_32khz_34000/G_34000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d88ac93665b86282dd81fa5725240c0a6dd45235d53ff85393c059a81d161f4
3
+ size 699513885
sovits_pinkie_32khz_34000/config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "eval_interval": 1000,
5
+ "seed": 1234,
6
+ "epochs": 10000,
7
+ "learning_rate": 0.0001,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 12,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 17920,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0,
21
+ "use_sr": true,
22
+ "max_speclen": 384,
23
+ "port": "8001"
24
+ },
25
+ "data": {
26
+ "training_files": "filelists/train.txt",
27
+ "validation_files": "filelists/val.txt",
28
+ "max_wav_value": 32768.0,
29
+ "sampling_rate": 32000,
30
+ "filter_length": 1280,
31
+ "hop_length": 320,
32
+ "win_length": 1280,
33
+ "n_mel_channels": 80,
34
+ "mel_fmin": 0.0,
35
+ "mel_fmax": null
36
+ },
37
+ "model": {
38
+ "inter_channels": 192,
39
+ "hidden_channels": 192,
40
+ "filter_channels": 768,
41
+ "n_heads": 2,
42
+ "n_layers": 6,
43
+ "kernel_size": 3,
44
+ "p_dropout": 0.1,
45
+ "resblock": "1",
46
+ "resblock_kernel_sizes": [
47
+ 3,
48
+ 7,
49
+ 11
50
+ ],
51
+ "resblock_dilation_sizes": [
52
+ [
53
+ 1,
54
+ 3,
55
+ 5
56
+ ],
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ]
67
+ ],
68
+ "upsample_rates": [
69
+ 10,
70
+ 8,
71
+ 2,
72
+ 2
73
+ ],
74
+ "upsample_initial_channel": 512,
75
+ "upsample_kernel_sizes": [
76
+ 16,
77
+ 16,
78
+ 4,
79
+ 4
80
+ ],
81
+ "n_layers_q": 3,
82
+ "use_spectral_norm": false,
83
+ "gin_channels": 256,
84
+ "ssl_dim": 256,
85
+ "n_speakers": 2
86
+ },
87
+ "spk": {
88
+ "pinkie": 0
89
+ }
90
+ }