Hugging Face's logo

Anonlestia
/
RVC_MLP_Models

English
Model card Files
xet
Anonlestia commited on
Commit
60008dd
·
verified ·
1 Parent(s): fe063b6

Delete so_vits_svc_3

Browse files
Files changed (22) hide show
  1. so_vits_svc_3/Arizona (TFH)/G_20000.pth +0 -3
  2. so_vits_svc_3/Arizona (TFH)/README.txt +0 -4
  3. so_vits_svc_3/Arizona (TFH)/config.json +0 -93
  4. so_vits_svc_3/Athena/G_25000.pth +0 -3
  5. so_vits_svc_3/Athena/README.txt +0 -4
  6. so_vits_svc_3/Athena/config.json +0 -93
  7. so_vits_svc_3/Cadance/G_10000.pth +0 -3
  8. so_vits_svc_3/Cadance/README.txt +0 -4
  9. so_vits_svc_3/Cadance/config.json +0 -94
  10. so_vits_svc_3/Derpy Hooves/G_20000.pth +0 -3
  11. so_vits_svc_3/Derpy Hooves/README.txt +0 -4
  12. so_vits_svc_3/Derpy Hooves/config.json +0 -94
  13. so_vits_svc_3/Saffron Masala/G_15000.pth +0 -3
  14. so_vits_svc_3/Saffron Masala/README.txt +0 -4
  15. so_vits_svc_3/Saffron Masala/config.json +0 -94
  16. so_vits_svc_3/Shining Armor/G_25000.pth +0 -3
  17. so_vits_svc_3/Shining Armor/README.txt +0 -4
  18. so_vits_svc_3/Shining Armor/config.json +0 -93
  19. so_vits_svc_3/Trixie Lulamoon/speaker.json +0 -3
  20. so_vits_svc_3/Velvet (TFH)/G_20000.pth +0 -3
  21. so_vits_svc_3/Velvet (TFH)/README.txt +0 -4
  22. so_vits_svc_3/Velvet (TFH)/config.json +0 -93
so_vits_svc_3/Arizona (TFH)/G_20000.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:94eaefdd69441b119bdeeb8166fe05b70f70018eef2c7344bf3cc301017f4af7
3
- size 542789405
 
 
 
 
so_vits_svc_3/Arizona (TFH)/README.txt DELETED
@@ -1,4 +0,0 @@
1
- Originally uploaded by Hazy Skies:
2
- https://huggingface.co/datasets/HazySkies/SV3/tree/main
3
- The zip file contained a training file which was not needed for inference,
4
- so I have reuploaded just the necessary files to the reduce download time for Hay Say.
 
 
 
 
 
so_vits_svc_3/Arizona (TFH)/config.json DELETED
@@ -1,93 +0,0 @@
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": 6,
14
- "fp16_run": false,
15
- "lr_decay": 0.999875,
16
- "segment_size": 10240,
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": 512,
23
- "port": "8001",
24
- "keep_ckpts": 3
25
- },
26
- "data": {
27
- "training_files": "filelists/train.txt",
28
- "validation_files": "filelists/val.txt",
29
- "max_wav_value": 32768.0,
30
- "sampling_rate": 44100,
31
- "filter_length": 2048,
32
- "hop_length": 512,
33
- "win_length": 2048,
34
- "n_mel_channels": 80,
35
- "mel_fmin": 0.0,
36
- "mel_fmax": 22050
37
- },
38
- "model": {
39
- "inter_channels": 192,
40
- "hidden_channels": 192,
41
- "filter_channels": 768,
42
- "n_heads": 2,
43
- "n_layers": 6,
44
- "kernel_size": 3,
45
- "p_dropout": 0.1,
46
- "resblock": "1",
47
- "resblock_kernel_sizes": [
48
- 3,
49
- 7,
50
- 11
51
- ],
52
- "resblock_dilation_sizes": [
53
- [
54
- 1,
55
- 3,
56
- 5
57
- ],
58
- [
59
- 1,
60
- 3,
61
- 5
62
- ],
63
- [
64
- 1,
65
- 3,
66
- 5
67
- ]
68
- ],
69
- "upsample_rates": [
70
- 8,
71
- 8,
72
- 2,
73
- 2,
74
- 2
75
- ],
76
- "upsample_initial_channel": 512,
77
- "upsample_kernel_sizes": [
78
- 16,
79
- 16,
80
- 4,
81
- 4,
82
- 4
83
- ],
84
- "n_layers_q": 3,
85
- "use_spectral_norm": false,
86
- "gin_channels": 256,
87
- "ssl_dim": 256,
88
- "n_speakers": 200
89
- },
90
- "spk": {
91
- "TFH_Arizona": 0
92
- }
93
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
so_vits_svc_3/Athena/G_25000.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8536b9686cde9b5d288c9539857224f69d70fc5b10edbc4245d639c3fd306e01
3
- size 542789405
 
 
 
 
so_vits_svc_3/Athena/README.txt DELETED
@@ -1,4 +0,0 @@
1
- Originally uploaded by Hazy Skies:
2
- https://huggingface.co/datasets/HazySkies/SV3/tree/main
3
- The zip file contained a training file which was not needed for inference,
4
- so I have reuploaded just the necessary files to the reduce download time for Hay Say.
 
 
 
 
 
so_vits_svc_3/Athena/config.json DELETED
@@ -1,93 +0,0 @@
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": 6,
14
- "fp16_run": false,
15
- "lr_decay": 0.999875,
16
- "segment_size": 10240,
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": 512,
23
- "port": "8001",
24
- "keep_ckpts": 3
25
- },
26
- "data": {
27
- "training_files": "filelists/train.txt",
28
- "validation_files": "filelists/val.txt",
29
- "max_wav_value": 32768.0,
30
- "sampling_rate": 44100,
31
- "filter_length": 2048,
32
- "hop_length": 512,
33
- "win_length": 2048,
34
- "n_mel_channels": 80,
35
- "mel_fmin": 0.0,
36
- "mel_fmax": 22050
37
- },
38
- "model": {
39
- "inter_channels": 192,
40
- "hidden_channels": 192,
41
- "filter_channels": 768,
42
- "n_heads": 2,
43
- "n_layers": 6,
44
- "kernel_size": 3,
45
- "p_dropout": 0.1,
46
- "resblock": "1",
47
- "resblock_kernel_sizes": [
48
- 3,
49
- 7,
50
- 11
51
- ],
52
- "resblock_dilation_sizes": [
53
- [
54
- 1,
55
- 3,
56
- 5
57
- ],
58
- [
59
- 1,
60
- 3,
61
- 5
62
- ],
63
- [
64
- 1,
65
- 3,
66
- 5
67
- ]
68
- ],
69
- "upsample_rates": [
70
- 8,
71
- 8,
72
- 2,
73
- 2,
74
- 2
75
- ],
76
- "upsample_initial_channel": 512,
77
- "upsample_kernel_sizes": [
78
- 16,
79
- 16,
80
- 4,
81
- 4,
82
- 4
83
- ],
84
- "n_layers_q": 3,
85
- "use_spectral_norm": false,
86
- "gin_channels": 256,
87
- "ssl_dim": 256,
88
- "n_speakers": 200
89
- },
90
- "spk": {
91
- "athena": 0
92
- }
93
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
so_vits_svc_3/Cadance/G_10000.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad492d00306396fc8c698d7bec1fe8bf17c07560084da623cf1f990da61cdac5
3
- size 548687709
 
 
 
 
so_vits_svc_3/Cadance/README.txt DELETED
@@ -1,4 +0,0 @@
1
- Originally uploaded by Hazy Skies:
2
- https://huggingface.co/datasets/HazySkies/SV3/tree/main
3
- The zip file contained a training file which was not needed for inference,
4
- so I have reuploaded just the necessary files to the reduce download time for Hay Say.
 
 
 
 
 
so_vits_svc_3/Cadance/config.json DELETED
@@ -1,94 +0,0 @@
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": 6,
14
- "fp16_run": false,
15
- "lr_decay": 0.999875,
16
- "segment_size": 10240,
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": 512,
23
- "port": "8001",
24
- "keep_ckpts": 3
25
- },
26
- "data": {
27
- "training_files": "filelists/train.txt",
28
- "validation_files": "filelists/val.txt",
29
- "max_wav_value": 32768.0,
30
- "sampling_rate": 44100,
31
- "filter_length": 2048,
32
- "hop_length": 512,
33
- "win_length": 2048,
34
- "n_mel_channels": 80,
35
- "mel_fmin": 0.0,
36
- "mel_fmax": 22050,
37
- "contentvec_final_proj": false
38
- },
39
- "model": {
40
- "inter_channels": 192,
41
- "hidden_channels": 192,
42
- "filter_channels": 768,
43
- "n_heads": 2,
44
- "n_layers": 6,
45
- "kernel_size": 3,
46
- "p_dropout": 0.1,
47
- "resblock": "1",
48
- "resblock_kernel_sizes": [
49
- 3,
50
- 7,
51
- 11
52
- ],
53
- "resblock_dilation_sizes": [
54
- [
55
- 1,
56
- 3,
57
- 5
58
- ],
59
- [
60
- 1,
61
- 3,
62
- 5
63
- ],
64
- [
65
- 1,
66
- 3,
67
- 5
68
- ]
69
- ],
70
- "upsample_rates": [
71
- 8,
72
- 8,
73
- 2,
74
- 2,
75
- 2
76
- ],
77
- "upsample_initial_channel": 512,
78
- "upsample_kernel_sizes": [
79
- 16,
80
- 16,
81
- 4,
82
- 4,
83
- 4
84
- ],
85
- "n_layers_q": 3,
86
- "use_spectral_norm": false,
87
- "gin_channels": 256,
88
- "ssl_dim": 768,
89
- "n_speakers": 200
90
- },
91
- "spk": {
92
- "Cadance": 0
93
- }
94
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
so_vits_svc_3/Derpy Hooves/G_20000.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ed2e62d83b4c92e3062cb77f080977f62e6c3c954229f71c3df2d4c74d6717d
3
- size 548687709
 
 
 
 
so_vits_svc_3/Derpy Hooves/README.txt DELETED
@@ -1,4 +0,0 @@
1
- Originally uploaded by Hazy Skies:
2
- https://huggingface.co/datasets/HazySkies/SV3/tree/main
3
- The zip file contained a training file which was not needed for inference,
4
- so I have reuploaded just the necessary files to the reduce download time for Hay Say.
 
 
 
 
 
so_vits_svc_3/Derpy Hooves/config.json DELETED
@@ -1,94 +0,0 @@
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": 6,
14
- "fp16_run": false,
15
- "lr_decay": 0.999875,
16
- "segment_size": 10240,
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": 512,
23
- "port": "8001",
24
- "keep_ckpts": 3
25
- },
26
- "data": {
27
- "training_files": "filelists/train.txt",
28
- "validation_files": "filelists/val.txt",
29
- "max_wav_value": 32768.0,
30
- "sampling_rate": 44100,
31
- "filter_length": 2048,
32
- "hop_length": 512,
33
- "win_length": 2048,
34
- "n_mel_channels": 80,
35
- "mel_fmin": 0.0,
36
- "mel_fmax": 22050,
37
- "contentvec_final_proj": false
38
- },
39
- "model": {
40
- "inter_channels": 192,
41
- "hidden_channels": 192,
42
- "filter_channels": 768,
43
- "n_heads": 2,
44
- "n_layers": 6,
45
- "kernel_size": 3,
46
- "p_dropout": 0.1,
47
- "resblock": "1",
48
- "resblock_kernel_sizes": [
49
- 3,
50
- 7,
51
- 11
52
- ],
53
- "resblock_dilation_sizes": [
54
- [
55
- 1,
56
- 3,
57
- 5
58
- ],
59
- [
60
- 1,
61
- 3,
62
- 5
63
- ],
64
- [
65
- 1,
66
- 3,
67
- 5
68
- ]
69
- ],
70
- "upsample_rates": [
71
- 8,
72
- 8,
73
- 2,
74
- 2,
75
- 2
76
- ],
77
- "upsample_initial_channel": 512,
78
- "upsample_kernel_sizes": [
79
- 16,
80
- 16,
81
- 4,
82
- 4,
83
- 4
84
- ],
85
- "n_layers_q": 3,
86
- "use_spectral_norm": false,
87
- "gin_channels": 256,
88
- "ssl_dim": 768,
89
- "n_speakers": 200
90
- },
91
- "spk": {
92
- "Derpy (SOL_BGE)": 0
93
- }
94
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
so_vits_svc_3/Saffron Masala/G_15000.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:18d65e35524a4e16da0c3136c56fa0485cea6ac058431bffcc6e68c0226357bc
3
- size 548687709
 
 
 
 
so_vits_svc_3/Saffron Masala/README.txt DELETED
@@ -1,4 +0,0 @@
1
- Originally uploaded by Hazy Skies:
2
- https://huggingface.co/datasets/HazySkies/SV3/tree/main
3
- The zip file contained a training file which was not needed for inference,
4
- so I have reuploaded just the necessary files to the reduce download time for Hay Say.
 
 
 
 
 
so_vits_svc_3/Saffron Masala/config.json DELETED
@@ -1,94 +0,0 @@
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": 6,
14
- "fp16_run": false,
15
- "lr_decay": 0.999875,
16
- "segment_size": 10240,
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": 512,
23
- "port": "8001",
24
- "keep_ckpts": 3
25
- },
26
- "data": {
27
- "training_files": "filelists/train.txt",
28
- "validation_files": "filelists/val.txt",
29
- "max_wav_value": 32768.0,
30
- "sampling_rate": 44100,
31
- "filter_length": 2048,
32
- "hop_length": 512,
33
- "win_length": 2048,
34
- "n_mel_channels": 80,
35
- "mel_fmin": 0.0,
36
- "mel_fmax": 22050,
37
- "contentvec_final_proj": false
38
- },
39
- "model": {
40
- "inter_channels": 192,
41
- "hidden_channels": 192,
42
- "filter_channels": 768,
43
- "n_heads": 2,
44
- "n_layers": 6,
45
- "kernel_size": 3,
46
- "p_dropout": 0.1,
47
- "resblock": "1",
48
- "resblock_kernel_sizes": [
49
- 3,
50
- 7,
51
- 11
52
- ],
53
- "resblock_dilation_sizes": [
54
- [
55
- 1,
56
- 3,
57
- 5
58
- ],
59
- [
60
- 1,
61
- 3,
62
- 5
63
- ],
64
- [
65
- 1,
66
- 3,
67
- 5
68
- ]
69
- ],
70
- "upsample_rates": [
71
- 8,
72
- 8,
73
- 2,
74
- 2,
75
- 2
76
- ],
77
- "upsample_initial_channel": 512,
78
- "upsample_kernel_sizes": [
79
- 16,
80
- 16,
81
- 4,
82
- 4,
83
- 4
84
- ],
85
- "n_layers_q": 3,
86
- "use_spectral_norm": false,
87
- "gin_channels": 256,
88
- "ssl_dim": 768,
89
- "n_speakers": 200
90
- },
91
- "spk": {
92
- "Saffron": 0
93
- }
94
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
so_vits_svc_3/Shining Armor/G_25000.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cee661c6afd4085b789e402d6dfe88418d0453cbcd2d52333d5d05a7f2f0cd3
3
- size 542789469
 
 
 
 
so_vits_svc_3/Shining Armor/README.txt DELETED
@@ -1,4 +0,0 @@
1
- Originally uploaded by Hazy Skies:
2
- https://huggingface.co/datasets/HazySkies/SV3/tree/main
3
- The zip file contained a training file which was not needed for inference,
4
- so I have reuploaded just the necessary files to the reduce download time for Hay Say.
 
 
 
 
 
so_vits_svc_3/Shining Armor/config.json DELETED
@@ -1,93 +0,0 @@
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": 6,
14
- "fp16_run": false,
15
- "lr_decay": 0.999875,
16
- "segment_size": 10240,
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": 512,
23
- "port": "8001",
24
- "keep_ckpts": 3
25
- },
26
- "data": {
27
- "training_files": "filelists/train.txt",
28
- "validation_files": "filelists/val.txt",
29
- "max_wav_value": 32768.0,
30
- "sampling_rate": 44100,
31
- "filter_length": 2048,
32
- "hop_length": 512,
33
- "win_length": 2048,
34
- "n_mel_channels": 80,
35
- "mel_fmin": 0.0,
36
- "mel_fmax": 22050
37
- },
38
- "model": {
39
- "inter_channels": 192,
40
- "hidden_channels": 192,
41
- "filter_channels": 768,
42
- "n_heads": 2,
43
- "n_layers": 6,
44
- "kernel_size": 3,
45
- "p_dropout": 0.1,
46
- "resblock": "1",
47
- "resblock_kernel_sizes": [
48
- 3,
49
- 7,
50
- 11
51
- ],
52
- "resblock_dilation_sizes": [
53
- [
54
- 1,
55
- 3,
56
- 5
57
- ],
58
- [
59
- 1,
60
- 3,
61
- 5
62
- ],
63
- [
64
- 1,
65
- 3,
66
- 5
67
- ]
68
- ],
69
- "upsample_rates": [
70
- 8,
71
- 8,
72
- 2,
73
- 2,
74
- 2
75
- ],
76
- "upsample_initial_channel": 512,
77
- "upsample_kernel_sizes": [
78
- 16,
79
- 16,
80
- 4,
81
- 4,
82
- 4
83
- ],
84
- "n_layers_q": 3,
85
- "use_spectral_norm": false,
86
- "gin_channels": 256,
87
- "ssl_dim": 256,
88
- "n_speakers": 200
89
- },
90
- "spk": {
91
- "ShiningArmor": 0
92
- }
93
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
so_vits_svc_3/Trixie Lulamoon/speaker.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "speaker": "trixie"
3
- }
 
 
 
 
so_vits_svc_3/Velvet (TFH)/G_20000.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f07dea548e7fd6c4d5371047a539831c18afcce354486bc94b82ede9bb88092
3
- size 542789405
 
 
 
 
so_vits_svc_3/Velvet (TFH)/README.txt DELETED
@@ -1,4 +0,0 @@
1
- Originally uploaded by Hazy Skies:
2
- https://huggingface.co/datasets/HazySkies/SV3/tree/main
3
- The zip file contained a training file which was not needed for inference,
4
- so I have reuploaded just the necessary files to the reduce download time for Hay Say.
 
 
 
 
 
so_vits_svc_3/Velvet (TFH)/config.json DELETED
@@ -1,93 +0,0 @@
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": 6,
14
- "fp16_run": false,
15
- "lr_decay": 0.999875,
16
- "segment_size": 10240,
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": 512,
23
- "port": "8001",
24
- "keep_ckpts": 3
25
- },
26
- "data": {
27
- "training_files": "filelists/train.txt",
28
- "validation_files": "filelists/val.txt",
29
- "max_wav_value": 32768.0,
30
- "sampling_rate": 44100,
31
- "filter_length": 2048,
32
- "hop_length": 512,
33
- "win_length": 2048,
34
- "n_mel_channels": 80,
35
- "mel_fmin": 0.0,
36
- "mel_fmax": 22050
37
- },
38
- "model": {
39
- "inter_channels": 192,
40
- "hidden_channels": 192,
41
- "filter_channels": 768,
42
- "n_heads": 2,
43
- "n_layers": 6,
44
- "kernel_size": 3,
45
- "p_dropout": 0.1,
46
- "resblock": "1",
47
- "resblock_kernel_sizes": [
48
- 3,
49
- 7,
50
- 11
51
- ],
52
- "resblock_dilation_sizes": [
53
- [
54
- 1,
55
- 3,
56
- 5
57
- ],
58
- [
59
- 1,
60
- 3,
61
- 5
62
- ],
63
- [
64
- 1,
65
- 3,
66
- 5
67
- ]
68
- ],
69
- "upsample_rates": [
70
- 8,
71
- 8,
72
- 2,
73
- 2,
74
- 2
75
- ],
76
- "upsample_initial_channel": 512,
77
- "upsample_kernel_sizes": [
78
- 16,
79
- 16,
80
- 4,
81
- 4,
82
- 4
83
- ],
84
- "n_layers_q": 3,
85
- "use_spectral_norm": false,
86
- "gin_channels": 256,
87
- "ssl_dim": 256,
88
- "n_speakers": 200
89
- },
90
- "spk": {
91
- "TFH_Velvet": 0
92
- }
93
- }