Hugging Face's logo

oItsMineZ
/
oItsMineZ-so-vits-svc-4.0-Model

Audio-to-Audio
Thai
English
Allar
ipynb
so-vits-svc
so-vits-svc-4.0
oitsminez
model
voicemodel
Model card Files Community
oItsMineZ commited on
Commit
43493ff
•
1 Parent(s): 100c3d7

Upload 15 files

Browse files
Files changed (15) hide show
  1. DaengGuitar/DaengGuitar.png +0 -0
  2. DaengGuitar/DaengGuitar.pth +3 -0
  3. DaengGuitar/config.json +104 -0
  4. Prayut/Prayut.png +0 -0
  5. Prayut/Prayut.pth +3 -0
  6. Prayut/config.json +104 -0
  7. RedremasteRed/RedremasteRed.jpg +0 -0
  8. RedremasteRed/RedremasteRed.pth +3 -0
  9. RedremasteRed/config.json +104 -0
  10. Sadsada/Sadsada.jpg +0 -0
  11. Sadsada/Sadsada.pth +3 -0
  12. Sadsada/config.json +104 -0
  13. TAEEXZENFIRE/TAEEXZENFIRE.jpg +0 -0
  14. TAEEXZENFIRE/TAEEXZENFIRE.pth +3 -0
  15. TAEEXZENFIRE/config.json +104 -0
DaengGuitar/DaengGuitar.png ADDED
DaengGuitar/DaengGuitar.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87cffe44c0e8c8086d27994c133cac9741ff965fbd1904d5879db378386ec8f9
3
+ size 548687709
DaengGuitar/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
4
+ "eval_interval": 200,
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": 16,
14
+ "fp16_run": false,
15
+ "bf16_run": false,
16
+ "lr_decay": 0.999875,
17
+ "segment_size": 10240,
18
+ "init_lr_ratio": 1,
19
+ "warmup_epochs": 0,
20
+ "c_mel": 45,
21
+ "c_kl": 1.0,
22
+ "use_sr": true,
23
+ "max_speclen": 512,
24
+ "port": "8001",
25
+ "keep_ckpts": 3,
26
+ "num_workers": 4,
27
+ "log_version": 0,
28
+ "ckpt_name_by_step": false,
29
+ "accumulate_grad_batches": 1
30
+ },
31
+ "data": {
32
+ "training_files": "filelists/44k/train.txt",
33
+ "validation_files": "filelists/44k/val.txt",
34
+ "max_wav_value": 32768.0,
35
+ "sampling_rate": 44100,
36
+ "filter_length": 2048,
37
+ "hop_length": 512,
38
+ "win_length": 2048,
39
+ "n_mel_channels": 80,
40
+ "mel_fmin": 0.0,
41
+ "mel_fmax": 22050,
42
+ "contentvec_final_proj": false
43
+ },
44
+ "model": {
45
+ "inter_channels": 192,
46
+ "hidden_channels": 192,
47
+ "filter_channels": 768,
48
+ "n_heads": 2,
49
+ "n_layers": 6,
50
+ "kernel_size": 3,
51
+ "p_dropout": 0.1,
52
+ "resblock": "1",
53
+ "resblock_kernel_sizes": [
54
+ 3,
55
+ 7,
56
+ 11
57
+ ],
58
+ "resblock_dilation_sizes": [
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ],
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ]
74
+ ],
75
+ "upsample_rates": [
76
+ 8,
77
+ 8,
78
+ 2,
79
+ 2,
80
+ 2
81
+ ],
82
+ "upsample_initial_channel": 512,
83
+ "upsample_kernel_sizes": [
84
+ 16,
85
+ 16,
86
+ 4,
87
+ 4,
88
+ 4
89
+ ],
90
+ "n_layers_q": 3,
91
+ "use_spectral_norm": false,
92
+ "gin_channels": 256,
93
+ "ssl_dim": 768,
94
+ "n_speakers": 200,
95
+ "type_": "hifi-gan",
96
+ "pretrained": {
97
+ "D_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth",
98
+ "G_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth"
99
+ }
100
+ },
101
+ "spk": {
102
+ "DaengGuitar": 0
103
+ }
104
+ }
Prayut/Prayut.png ADDED
Prayut/Prayut.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba3a76fbc830113e1f4a4ba704df4256e6d16cb3db668e5bfb04b9a1caa7338
3
+ size 548687709
Prayut/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
4
+ "eval_interval": 200,
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": 16,
14
+ "fp16_run": false,
15
+ "bf16_run": false,
16
+ "lr_decay": 0.999875,
17
+ "segment_size": 10240,
18
+ "init_lr_ratio": 1,
19
+ "warmup_epochs": 0,
20
+ "c_mel": 45,
21
+ "c_kl": 1.0,
22
+ "use_sr": true,
23
+ "max_speclen": 512,
24
+ "port": "8001",
25
+ "keep_ckpts": 3,
26
+ "num_workers": 4,
27
+ "log_version": 0,
28
+ "ckpt_name_by_step": false,
29
+ "accumulate_grad_batches": 1
30
+ },
31
+ "data": {
32
+ "training_files": "filelists/44k/train.txt",
33
+ "validation_files": "filelists/44k/val.txt",
34
+ "max_wav_value": 32768.0,
35
+ "sampling_rate": 44100,
36
+ "filter_length": 2048,
37
+ "hop_length": 512,
38
+ "win_length": 2048,
39
+ "n_mel_channels": 80,
40
+ "mel_fmin": 0.0,
41
+ "mel_fmax": 22050,
42
+ "contentvec_final_proj": false
43
+ },
44
+ "model": {
45
+ "inter_channels": 192,
46
+ "hidden_channels": 192,
47
+ "filter_channels": 768,
48
+ "n_heads": 2,
49
+ "n_layers": 6,
50
+ "kernel_size": 3,
51
+ "p_dropout": 0.1,
52
+ "resblock": "1",
53
+ "resblock_kernel_sizes": [
54
+ 3,
55
+ 7,
56
+ 11
57
+ ],
58
+ "resblock_dilation_sizes": [
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ],
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ]
74
+ ],
75
+ "upsample_rates": [
76
+ 8,
77
+ 8,
78
+ 2,
79
+ 2,
80
+ 2
81
+ ],
82
+ "upsample_initial_channel": 512,
83
+ "upsample_kernel_sizes": [
84
+ 16,
85
+ 16,
86
+ 4,
87
+ 4,
88
+ 4
89
+ ],
90
+ "n_layers_q": 3,
91
+ "use_spectral_norm": false,
92
+ "gin_channels": 256,
93
+ "ssl_dim": 768,
94
+ "n_speakers": 200,
95
+ "type_": "hifi-gan",
96
+ "pretrained": {
97
+ "D_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth",
98
+ "G_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth"
99
+ }
100
+ },
101
+ "spk": {
102
+ "Prayut": 0
103
+ }
104
+ }
RedremasteRed/RedremasteRed.jpg ADDED
RedremasteRed/RedremasteRed.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62a2bbfbd6e84829ae7e05f2e8792eb3beaa2ba412bb3e0e180924ad7b7cab2
3
+ size 548687709
RedremasteRed/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
4
+ "eval_interval": 200,
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": 16,
14
+ "fp16_run": false,
15
+ "bf16_run": false,
16
+ "lr_decay": 0.999875,
17
+ "segment_size": 10240,
18
+ "init_lr_ratio": 1,
19
+ "warmup_epochs": 0,
20
+ "c_mel": 45,
21
+ "c_kl": 1.0,
22
+ "use_sr": true,
23
+ "max_speclen": 512,
24
+ "port": "8001",
25
+ "keep_ckpts": 3,
26
+ "num_workers": 4,
27
+ "log_version": 0,
28
+ "ckpt_name_by_step": false,
29
+ "accumulate_grad_batches": 1
30
+ },
31
+ "data": {
32
+ "training_files": "filelists/44k/train.txt",
33
+ "validation_files": "filelists/44k/val.txt",
34
+ "max_wav_value": 32768.0,
35
+ "sampling_rate": 44100,
36
+ "filter_length": 2048,
37
+ "hop_length": 512,
38
+ "win_length": 2048,
39
+ "n_mel_channels": 80,
40
+ "mel_fmin": 0.0,
41
+ "mel_fmax": 22050,
42
+ "contentvec_final_proj": false
43
+ },
44
+ "model": {
45
+ "inter_channels": 192,
46
+ "hidden_channels": 192,
47
+ "filter_channels": 768,
48
+ "n_heads": 2,
49
+ "n_layers": 6,
50
+ "kernel_size": 3,
51
+ "p_dropout": 0.1,
52
+ "resblock": "1",
53
+ "resblock_kernel_sizes": [
54
+ 3,
55
+ 7,
56
+ 11
57
+ ],
58
+ "resblock_dilation_sizes": [
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ],
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ]
74
+ ],
75
+ "upsample_rates": [
76
+ 8,
77
+ 8,
78
+ 2,
79
+ 2,
80
+ 2
81
+ ],
82
+ "upsample_initial_channel": 512,
83
+ "upsample_kernel_sizes": [
84
+ 16,
85
+ 16,
86
+ 4,
87
+ 4,
88
+ 4
89
+ ],
90
+ "n_layers_q": 3,
91
+ "use_spectral_norm": false,
92
+ "gin_channels": 256,
93
+ "ssl_dim": 768,
94
+ "n_speakers": 200,
95
+ "type_": "hifi-gan",
96
+ "pretrained": {
97
+ "D_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth",
98
+ "G_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth"
99
+ }
100
+ },
101
+ "spk": {
102
+ "Red": 0
103
+ }
104
+ }
Sadsada/Sadsada.jpg ADDED
Sadsada/Sadsada.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5dd69005f74fb24fafb8d0585f929328bab32271518ee7a3e41356e0f6b7c2
3
+ size 548687709
Sadsada/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
4
+ "eval_interval": 200,
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": 16,
14
+ "fp16_run": false,
15
+ "bf16_run": false,
16
+ "lr_decay": 0.999875,
17
+ "segment_size": 10240,
18
+ "init_lr_ratio": 1,
19
+ "warmup_epochs": 0,
20
+ "c_mel": 45,
21
+ "c_kl": 1.0,
22
+ "use_sr": true,
23
+ "max_speclen": 512,
24
+ "port": "8001",
25
+ "keep_ckpts": 3,
26
+ "num_workers": 4,
27
+ "log_version": 0,
28
+ "ckpt_name_by_step": false,
29
+ "accumulate_grad_batches": 1
30
+ },
31
+ "data": {
32
+ "training_files": "filelists/44k/train.txt",
33
+ "validation_files": "filelists/44k/val.txt",
34
+ "max_wav_value": 32768.0,
35
+ "sampling_rate": 44100,
36
+ "filter_length": 2048,
37
+ "hop_length": 512,
38
+ "win_length": 2048,
39
+ "n_mel_channels": 80,
40
+ "mel_fmin": 0.0,
41
+ "mel_fmax": 22050,
42
+ "contentvec_final_proj": false
43
+ },
44
+ "model": {
45
+ "inter_channels": 192,
46
+ "hidden_channels": 192,
47
+ "filter_channels": 768,
48
+ "n_heads": 2,
49
+ "n_layers": 6,
50
+ "kernel_size": 3,
51
+ "p_dropout": 0.1,
52
+ "resblock": "1",
53
+ "resblock_kernel_sizes": [
54
+ 3,
55
+ 7,
56
+ 11
57
+ ],
58
+ "resblock_dilation_sizes": [
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ],
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ]
74
+ ],
75
+ "upsample_rates": [
76
+ 8,
77
+ 8,
78
+ 2,
79
+ 2,
80
+ 2
81
+ ],
82
+ "upsample_initial_channel": 512,
83
+ "upsample_kernel_sizes": [
84
+ 16,
85
+ 16,
86
+ 4,
87
+ 4,
88
+ 4
89
+ ],
90
+ "n_layers_q": 3,
91
+ "use_spectral_norm": false,
92
+ "gin_channels": 256,
93
+ "ssl_dim": 768,
94
+ "n_speakers": 200,
95
+ "type_": "hifi-gan",
96
+ "pretrained": {
97
+ "D_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth",
98
+ "G_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth"
99
+ }
100
+ },
101
+ "spk": {
102
+ "Sadsada": 0
103
+ }
104
+ }
TAEEXZENFIRE/TAEEXZENFIRE.jpg ADDED
TAEEXZENFIRE/TAEEXZENFIRE.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39b71f496e6b7359915564c9c215aaf3e504e5a2ef71d9ef45acc6406858684
3
+ size 548687709
TAEEXZENFIRE/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
4
+ "eval_interval": 200,
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": 16,
14
+ "fp16_run": false,
15
+ "bf16_run": false,
16
+ "lr_decay": 0.999875,
17
+ "segment_size": 10240,
18
+ "init_lr_ratio": 1,
19
+ "warmup_epochs": 0,
20
+ "c_mel": 45,
21
+ "c_kl": 1.0,
22
+ "use_sr": true,
23
+ "max_speclen": 512,
24
+ "port": "8001",
25
+ "keep_ckpts": 3,
26
+ "num_workers": 4,
27
+ "log_version": 0,
28
+ "ckpt_name_by_step": false,
29
+ "accumulate_grad_batches": 1
30
+ },
31
+ "data": {
32
+ "training_files": "filelists/44k/train.txt",
33
+ "validation_files": "filelists/44k/val.txt",
34
+ "max_wav_value": 32768.0,
35
+ "sampling_rate": 44100,
36
+ "filter_length": 2048,
37
+ "hop_length": 512,
38
+ "win_length": 2048,
39
+ "n_mel_channels": 80,
40
+ "mel_fmin": 0.0,
41
+ "mel_fmax": 22050,
42
+ "contentvec_final_proj": false
43
+ },
44
+ "model": {
45
+ "inter_channels": 192,
46
+ "hidden_channels": 192,
47
+ "filter_channels": 768,
48
+ "n_heads": 2,
49
+ "n_layers": 6,
50
+ "kernel_size": 3,
51
+ "p_dropout": 0.1,
52
+ "resblock": "1",
53
+ "resblock_kernel_sizes": [
54
+ 3,
55
+ 7,
56
+ 11
57
+ ],
58
+ "resblock_dilation_sizes": [
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ],
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ]
74
+ ],
75
+ "upsample_rates": [
76
+ 8,
77
+ 8,
78
+ 2,
79
+ 2,
80
+ 2
81
+ ],
82
+ "upsample_initial_channel": 512,
83
+ "upsample_kernel_sizes": [
84
+ 16,
85
+ 16,
86
+ 4,
87
+ 4,
88
+ 4
89
+ ],
90
+ "n_layers_q": 3,
91
+ "use_spectral_norm": false,
92
+ "gin_channels": 256,
93
+ "ssl_dim": 768,
94
+ "n_speakers": 200,
95
+ "type_": "hifi-gan",
96
+ "pretrained": {
97
+ "D_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth",
98
+ "G_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth"
99
+ }
100
+ },
101
+ "spk": {
102
+ "TAE": 0
103
+ }
104
+ }