Hugging Face's logo

therealvul
/
so-vits-svc-3.0

English
Model card Files Community
1
therealvul commited on
Commit
39d5cce
•
1 Parent(s): d5809f3

Upload 30 files

Browse files
Files changed (30) hide show
  1. Applebloom 3.0/D_55000.pth +3 -0
  2. Applebloom 3.0/G_55000.pth +3 -0
  3. Applebloom 3.0/config.json +90 -0
  4. Applejack 3.0/D_38000.pth +3 -0
  5. Applejack 3.0/G_38000.pth +3 -0
  6. Applejack 3.0/config.json +90 -0
  7. Celestia 3.0/D_15000.pth +3 -0
  8. Celestia 3.0/G_15000.pth +3 -0
  9. Celestia 3.0/config.json +90 -0
  10. Luna 3.0/D_12000.pth +3 -0
  11. Luna 3.0/G_12000.pth +3 -0
  12. Luna 3.0/config.json +90 -0
  13. RainbowDash 3.0/D_48000.pth +3 -0
  14. RainbowDash 3.0/G_48000.pth +3 -0
  15. RainbowDash 3.0/config.json +90 -0
  16. Rarity 3.0/D_43000.pth +3 -0
  17. Rarity 3.0/G_43000.pth +3 -0
  18. Rarity 3.0/config.json +90 -0
  19. Scootaloo 3.0/D_52000.pth +3 -0
  20. Scootaloo 3.0/G_52000.pth +3 -0
  21. Scootaloo 3.0/config.json +90 -0
  22. Starlight Glimmer 3.0/D_19000.pth +3 -0
  23. Starlight Glimmer 3.0/G_19000.pth +3 -0
  24. Starlight Glimmer 3.0/config.json +90 -0
  25. Sweetie Belle 3.0/D_37000.pth +3 -0
  26. Sweetie Belle 3.0/G_37000.pth +3 -0
  27. Sweetie Belle 3.0/config.json +90 -0
  28. TwilightSparkle 3.0/D_32000.pth +3 -0
  29. TwilightSparkle 3.0/G_32000.pth +3 -0
  30. TwilightSparkle 3.0/config.json +90 -0
Applebloom 3.0/D_55000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e86b304a738c7438c8ef0c0a66fce1b14861e7a333fde65ffc795f8cff9ab1
3
+ size 561070567
Applebloom 3.0/G_55000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25378a3d00679e9f3c9d2880da70b94dff0484c5a112318f2e3a3f784fc15a32
3
+ size 699313500
Applebloom 3.0/config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 10,
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": 8,
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
+ "Applebloom": 0
89
+ }
90
+ }
Applejack 3.0/D_38000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898bc766c80ca54e0593d2e02c8cea235348fcc2ed0f9d06fcf23a408ce8426d
3
+ size 561070567
Applejack 3.0/G_38000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2e909a104ea8319e878269931a747fbf4fa72f20b577f830efe4de1412351c
3
+ size 699313500
Applejack 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
+ "Applejack": 0
89
+ }
90
+ }
Celestia 3.0/D_15000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a561675344f991b45bbfbe45937e493caa1e58b54f53354308c84f2048137ee
3
+ size 561070567
Celestia 3.0/G_15000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea2385b45486126070c28af68d339062263a16f9d6f8dd4b193098fd5002881
3
+ size 699313500
Celestia 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
+ "Celestia (singing)": 0
89
+ }
90
+ }
Luna 3.0/D_12000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55371d36be52cb31a3e8c8b601032a4a89ae7de81de84e552ccab1feccbd460c
3
+ size 561070567
Luna 3.0/G_12000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ec779590313342ea3bb6202af6a746a2bfb16a78e505816d657ee481849ca9
3
+ size 699313500
Luna 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
+ "Luna": 0
89
+ }
90
+ }
RainbowDash 3.0/D_48000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ecaf6aabcd8738f2289d99dc4197f8283d23ba33f45ae8b5d0ff0316c50e5b
3
+ size 561070567
RainbowDash 3.0/G_48000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a0b7474eb4571e133a8aeeeda50668ba32eecbe30a89208193de5592505f11
3
+ size 699313500
RainbowDash 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
+ "RainbowDash": 0
89
+ }
90
+ }
Rarity 3.0/D_43000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b1e0ef0fa9bf237d6ad05c485d2a12e0f844e2c7a14835a6d5743be622d2d7
3
+ size 561070567
Rarity 3.0/G_43000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7e114dbf63251c3d71b191f744d74b1ef64b926d4cba617ef8a7e0272f32a6
3
+ size 699313500
Rarity 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": 0
89
+ }
90
+ }
Scootaloo 3.0/D_52000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa95fa3702b357af84386b77aca2cc042955ae386f11ab082d6ac12f7ee7920f
3
+ size 561070567
Scootaloo 3.0/G_52000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c086ae3c3afe6333013506ce434d7991a4fb99135982140e88a83de077abd74b
3
+ size 699313500
Scootaloo 3.0/config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 10,
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
+ "Scootaloo": 0
89
+ }
90
+ }
Starlight Glimmer 3.0/D_19000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8186244cf2e72e90eb6b2ef28649d80f7fdca7aec304a30ad41d4f78035b37
3
+ size 561070567
Starlight Glimmer 3.0/G_19000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f4bf0157e1b78bf25610bad7c19e128ef1e43a1a22cb2a94cc677d742b9b96
3
+ size 699313500
Starlight Glimmer 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
+ "Starlight Glimmer (singing)": 0
89
+ }
90
+ }
Sweetie Belle 3.0/D_37000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5291aee185e0e165d2a447135c19d6a27b4d9938e90784799d7f541dbb7d7620
3
+ size 561070567
Sweetie Belle 3.0/G_37000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3682a7c772a25fd48f172e952dfc0619f95ba5f14fc7a177b497602f773e68ce
3
+ size 699313500
Sweetie Belle 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
+ "SweetieBelle": 0
89
+ }
90
+ }
TwilightSparkle 3.0/D_32000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:360688979ad0f2e4b564230b0329241da6b7968f09b4deccac73239e493d53ee
3
+ size 561099401
TwilightSparkle 3.0/G_32000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9765b530ae037cef552512dad726f3b0f62ec783f5f64ec5064490c9963091aa
3
+ size 699513885
TwilightSparkle 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
+ "TwilightSparkle": 0
89
+ }
90
+ }