Hugging Face's logo

Wanlau
/
RVC_a-kiss-for-the-petals

Audio-to-Audio
RVC
Model card Files
xet
Community
Wanlau commited on
Commit
c7a7d65
·
1 Parent(s): 74f54c5

xinshidai

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. Ai_v2/Ai_v2.pth +3 -0
  3. Ai_v2/added_IVF4741_Flat_nprobe_1_Ai_v2_v2.index +3 -0
  4. Aya_v2/Aya_v2.pth +3 -0
  5. Aya_v2/added_IVF256_Flat_nprobe_1_Aya_v2_v2.index +3 -0
  6. Aya_v2/config.json +79 -0
  7. Haduki_v2/Haduki_v2.pth +3 -0
  8. Haduki_v2/added_IVF256_Flat_nprobe_1_Haduki_v2_v2.index +3 -0
  9. Haduki_v2/config.json +79 -0
  10. Manami_v2/Manami_v2.pth +3 -0
  11. Manami_v2/added_IVF256_Flat_nprobe_1_Manami_v2_v2.index +3 -0
  12. Manami_v2/config.json +79 -0
  13. Nagisa_v2/Nagisa_v2.pth +3 -0
  14. Nagisa_v2/added_IVF256_Flat_nprobe_1_Nagisa_v2_v2.index +3 -0
  15. Nagisa_v2/config.json +79 -0
  16. Rina_v2/Rina_v2.pth +3 -0
  17. Rina_v2/added_IVF256_Flat_nprobe_1_Rina_v2_v2.index +3 -0
  18. Rina_v2/config.json +79 -0
  19. Sara_v2/Sara_v2.pth +3 -0
  20. Sara_v2/added_IVF256_Flat_nprobe_1_Sara_v2_v2.index +3 -0
  21. Sara_v2/config.json +79 -0
.gitattributes CHANGED
@@ -53,3 +53,4 @@ Kaori/added_IVF4659_Flat_nprobe_1_v1.index filter=lfs diff=lfs merge=lfs -text
53
  Koharu/added_IVF2243_Flat_nprobe_1_v1.index filter=lfs diff=lfs merge=lfs -text
54
  Makoto/added_IVF1209_Flat_nprobe_1_v1.index filter=lfs diff=lfs merge=lfs -text
55
  Reo_v2/added_IVF10047_Flat_nprobe_1_v2.index filter=lfs diff=lfs merge=lfs -text
 
 
53
  Koharu/added_IVF2243_Flat_nprobe_1_v1.index filter=lfs diff=lfs merge=lfs -text
54
  Makoto/added_IVF1209_Flat_nprobe_1_v1.index filter=lfs diff=lfs merge=lfs -text
55
  Reo_v2/added_IVF10047_Flat_nprobe_1_v2.index filter=lfs diff=lfs merge=lfs -text
56
+ *.index filter=lfs diff=lfs merge=lfs -text
Ai_v2/Ai_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4255cbd499afa868d0eecb62784b4d86b19bd30a76ccd22ddd7dc43c65c7cd
3
+ size 55222703
Ai_v2/added_IVF4741_Flat_nprobe_1_Ai_v2_v2.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c7e96d72f38afc333b3d79bc51afe6debd65ac0e5aeee2622d6ca52823e581
3
+ size 584156019
Aya_v2/Aya_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0b14108412b0ed92a5bb7b27298e0c6b6a65c01cdd6e972c4ebf27a8b52770
3
+ size 55222703
Aya_v2/added_IVF256_Flat_nprobe_1_Aya_v2_v2.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f4f8637c667f3d425b36256f8c46819cd769ff13ff0c8b2de9544b58713dda
3
+ size 31588619
Aya_v2/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": {
3
+ "filter_length": 2048,
4
+ "hop_length": 400,
5
+ "max_wav_value": 32768.0,
6
+ "mel_fmax": null,
7
+ "mel_fmin": 0.0,
8
+ "n_mel_channels": 125,
9
+ "sampling_rate": 40000,
10
+ "win_length": 2048
11
+ },
12
+ "model": {
13
+ "filter_channels": 768,
14
+ "gin_channels": 256,
15
+ "hidden_channels": 192,
16
+ "inter_channels": 192,
17
+ "kernel_size": 3,
18
+ "n_heads": 2,
19
+ "n_layers": 6,
20
+ "p_dropout": 0,
21
+ "resblock": "1",
22
+ "resblock_dilation_sizes": [
23
+ [
24
+ 1,
25
+ 3,
26
+ 5
27
+ ],
28
+ [
29
+ 1,
30
+ 3,
31
+ 5
32
+ ],
33
+ [
34
+ 1,
35
+ 3,
36
+ 5
37
+ ]
38
+ ],
39
+ "resblock_kernel_sizes": [
40
+ 3,
41
+ 7,
42
+ 11
43
+ ],
44
+ "spk_embed_dim": 109,
45
+ "upsample_initial_channel": 512,
46
+ "upsample_kernel_sizes": [
47
+ 16,
48
+ 16,
49
+ 4,
50
+ 4
51
+ ],
52
+ "upsample_rates": [
53
+ 10,
54
+ 10,
55
+ 2,
56
+ 2
57
+ ],
58
+ "use_spectral_norm": false
59
+ },
60
+ "train": {
61
+ "batch_size": 4,
62
+ "betas": [
63
+ 0.8,
64
+ 0.99
65
+ ],
66
+ "c_kl": 1.0,
67
+ "c_mel": 45,
68
+ "epochs": 20000,
69
+ "eps": 1e-09,
70
+ "fp16_run": true,
71
+ "init_lr_ratio": 1,
72
+ "learning_rate": 0.0001,
73
+ "log_interval": 200,
74
+ "lr_decay": 0.999875,
75
+ "seed": 1234,
76
+ "segment_size": 12800,
77
+ "warmup_epochs": 0
78
+ }
79
+ }
Haduki_v2/Haduki_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1c0296b46ad17b04267570d08b5ae18ae908a9c76d92e4a2ed7cb77333373e
3
+ size 55222703
Haduki_v2/added_IVF256_Flat_nprobe_1_Haduki_v2_v2.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98eb1f965ea79f658d881471049061f96ee43f86bc3e2e16fbe2d876b0b55d6b
3
+ size 31588619
Haduki_v2/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": {
3
+ "filter_length": 2048,
4
+ "hop_length": 400,
5
+ "max_wav_value": 32768.0,
6
+ "mel_fmax": null,
7
+ "mel_fmin": 0.0,
8
+ "n_mel_channels": 125,
9
+ "sampling_rate": 40000,
10
+ "win_length": 2048
11
+ },
12
+ "model": {
13
+ "filter_channels": 768,
14
+ "gin_channels": 256,
15
+ "hidden_channels": 192,
16
+ "inter_channels": 192,
17
+ "kernel_size": 3,
18
+ "n_heads": 2,
19
+ "n_layers": 6,
20
+ "p_dropout": 0,
21
+ "resblock": "1",
22
+ "resblock_dilation_sizes": [
23
+ [
24
+ 1,
25
+ 3,
26
+ 5
27
+ ],
28
+ [
29
+ 1,
30
+ 3,
31
+ 5
32
+ ],
33
+ [
34
+ 1,
35
+ 3,
36
+ 5
37
+ ]
38
+ ],
39
+ "resblock_kernel_sizes": [
40
+ 3,
41
+ 7,
42
+ 11
43
+ ],
44
+ "spk_embed_dim": 109,
45
+ "upsample_initial_channel": 512,
46
+ "upsample_kernel_sizes": [
47
+ 16,
48
+ 16,
49
+ 4,
50
+ 4
51
+ ],
52
+ "upsample_rates": [
53
+ 10,
54
+ 10,
55
+ 2,
56
+ 2
57
+ ],
58
+ "use_spectral_norm": false
59
+ },
60
+ "train": {
61
+ "batch_size": 4,
62
+ "betas": [
63
+ 0.8,
64
+ 0.99
65
+ ],
66
+ "c_kl": 1.0,
67
+ "c_mel": 45,
68
+ "epochs": 20000,
69
+ "eps": 1e-09,
70
+ "fp16_run": true,
71
+ "init_lr_ratio": 1,
72
+ "learning_rate": 0.0001,
73
+ "log_interval": 200,
74
+ "lr_decay": 0.999875,
75
+ "seed": 1234,
76
+ "segment_size": 12800,
77
+ "warmup_epochs": 0
78
+ }
79
+ }
Manami_v2/Manami_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:245eabc842fd5c1a734da2d620a6211bf37c57c9e6baa8387bc57d261bdc972d
3
+ size 55222703
Manami_v2/added_IVF256_Flat_nprobe_1_Manami_v2_v2.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9a6e23c865329ab23b87c18d55adcd310cc75c9db8e6f8b16f27860e8816af6
3
+ size 31588619
Manami_v2/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": {
3
+ "filter_length": 2048,
4
+ "hop_length": 400,
5
+ "max_wav_value": 32768.0,
6
+ "mel_fmax": null,
7
+ "mel_fmin": 0.0,
8
+ "n_mel_channels": 125,
9
+ "sampling_rate": 40000,
10
+ "win_length": 2048
11
+ },
12
+ "model": {
13
+ "filter_channels": 768,
14
+ "gin_channels": 256,
15
+ "hidden_channels": 192,
16
+ "inter_channels": 192,
17
+ "kernel_size": 3,
18
+ "n_heads": 2,
19
+ "n_layers": 6,
20
+ "p_dropout": 0,
21
+ "resblock": "1",
22
+ "resblock_dilation_sizes": [
23
+ [
24
+ 1,
25
+ 3,
26
+ 5
27
+ ],
28
+ [
29
+ 1,
30
+ 3,
31
+ 5
32
+ ],
33
+ [
34
+ 1,
35
+ 3,
36
+ 5
37
+ ]
38
+ ],
39
+ "resblock_kernel_sizes": [
40
+ 3,
41
+ 7,
42
+ 11
43
+ ],
44
+ "spk_embed_dim": 109,
45
+ "upsample_initial_channel": 512,
46
+ "upsample_kernel_sizes": [
47
+ 16,
48
+ 16,
49
+ 4,
50
+ 4
51
+ ],
52
+ "upsample_rates": [
53
+ 10,
54
+ 10,
55
+ 2,
56
+ 2
57
+ ],
58
+ "use_spectral_norm": false
59
+ },
60
+ "train": {
61
+ "batch_size": 4,
62
+ "betas": [
63
+ 0.8,
64
+ 0.99
65
+ ],
66
+ "c_kl": 1.0,
67
+ "c_mel": 45,
68
+ "epochs": 20000,
69
+ "eps": 1e-09,
70
+ "fp16_run": true,
71
+ "init_lr_ratio": 1,
72
+ "learning_rate": 0.0001,
73
+ "log_interval": 200,
74
+ "lr_decay": 0.999875,
75
+ "seed": 1234,
76
+ "segment_size": 12800,
77
+ "warmup_epochs": 0
78
+ }
79
+ }
Nagisa_v2/Nagisa_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ce477ae0ac7991f1550cfde9020cc288b6e624bc0e09ddc7e3394cb1a58d09
3
+ size 55222703
Nagisa_v2/added_IVF256_Flat_nprobe_1_Nagisa_v2_v2.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150bf4bb2546ac00730c5e8adf771633d12094a6fd4710306968d44bb0ec925b
3
+ size 31588619
Nagisa_v2/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": {
3
+ "filter_length": 2048,
4
+ "hop_length": 400,
5
+ "max_wav_value": 32768.0,
6
+ "mel_fmax": null,
7
+ "mel_fmin": 0.0,
8
+ "n_mel_channels": 125,
9
+ "sampling_rate": 40000,
10
+ "win_length": 2048
11
+ },
12
+ "model": {
13
+ "filter_channels": 768,
14
+ "gin_channels": 256,
15
+ "hidden_channels": 192,
16
+ "inter_channels": 192,
17
+ "kernel_size": 3,
18
+ "n_heads": 2,
19
+ "n_layers": 6,
20
+ "p_dropout": 0,
21
+ "resblock": "1",
22
+ "resblock_dilation_sizes": [
23
+ [
24
+ 1,
25
+ 3,
26
+ 5
27
+ ],
28
+ [
29
+ 1,
30
+ 3,
31
+ 5
32
+ ],
33
+ [
34
+ 1,
35
+ 3,
36
+ 5
37
+ ]
38
+ ],
39
+ "resblock_kernel_sizes": [
40
+ 3,
41
+ 7,
42
+ 11
43
+ ],
44
+ "spk_embed_dim": 109,
45
+ "upsample_initial_channel": 512,
46
+ "upsample_kernel_sizes": [
47
+ 16,
48
+ 16,
49
+ 4,
50
+ 4
51
+ ],
52
+ "upsample_rates": [
53
+ 10,
54
+ 10,
55
+ 2,
56
+ 2
57
+ ],
58
+ "use_spectral_norm": false
59
+ },
60
+ "train": {
61
+ "batch_size": 4,
62
+ "betas": [
63
+ 0.8,
64
+ 0.99
65
+ ],
66
+ "c_kl": 1.0,
67
+ "c_mel": 45,
68
+ "epochs": 20000,
69
+ "eps": 1e-09,
70
+ "fp16_run": true,
71
+ "init_lr_ratio": 1,
72
+ "learning_rate": 0.0001,
73
+ "log_interval": 200,
74
+ "lr_decay": 0.999875,
75
+ "seed": 1234,
76
+ "segment_size": 12800,
77
+ "warmup_epochs": 0
78
+ }
79
+ }
Rina_v2/Rina_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:101c1389aad10643d689a204c8805c506902c8e1c59919b599cd8c156b9d1cc8
3
+ size 55222703
Rina_v2/added_IVF256_Flat_nprobe_1_Rina_v2_v2.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54df3020c06e7008ccc370b04787bce332773156ed005f39b5c8a66b43a9a1b2
3
+ size 31588619
Rina_v2/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": {
3
+ "filter_length": 2048,
4
+ "hop_length": 400,
5
+ "max_wav_value": 32768.0,
6
+ "mel_fmax": null,
7
+ "mel_fmin": 0.0,
8
+ "n_mel_channels": 125,
9
+ "sampling_rate": 40000,
10
+ "win_length": 2048
11
+ },
12
+ "model": {
13
+ "filter_channels": 768,
14
+ "gin_channels": 256,
15
+ "hidden_channels": 192,
16
+ "inter_channels": 192,
17
+ "kernel_size": 3,
18
+ "n_heads": 2,
19
+ "n_layers": 6,
20
+ "p_dropout": 0,
21
+ "resblock": "1",
22
+ "resblock_dilation_sizes": [
23
+ [
24
+ 1,
25
+ 3,
26
+ 5
27
+ ],
28
+ [
29
+ 1,
30
+ 3,
31
+ 5
32
+ ],
33
+ [
34
+ 1,
35
+ 3,
36
+ 5
37
+ ]
38
+ ],
39
+ "resblock_kernel_sizes": [
40
+ 3,
41
+ 7,
42
+ 11
43
+ ],
44
+ "spk_embed_dim": 109,
45
+ "upsample_initial_channel": 512,
46
+ "upsample_kernel_sizes": [
47
+ 16,
48
+ 16,
49
+ 4,
50
+ 4
51
+ ],
52
+ "upsample_rates": [
53
+ 10,
54
+ 10,
55
+ 2,
56
+ 2
57
+ ],
58
+ "use_spectral_norm": false
59
+ },
60
+ "train": {
61
+ "batch_size": 4,
62
+ "betas": [
63
+ 0.8,
64
+ 0.99
65
+ ],
66
+ "c_kl": 1.0,
67
+ "c_mel": 45,
68
+ "epochs": 20000,
69
+ "eps": 1e-09,
70
+ "fp16_run": true,
71
+ "init_lr_ratio": 1,
72
+ "learning_rate": 0.0001,
73
+ "log_interval": 200,
74
+ "lr_decay": 0.999875,
75
+ "seed": 1234,
76
+ "segment_size": 12800,
77
+ "warmup_epochs": 0
78
+ }
79
+ }
Sara_v2/Sara_v2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652fe01804252d3d45af852aa1518ed7c3c2aae5ed38c1102ce016c8dae3e942
3
+ size 55222703
Sara_v2/added_IVF256_Flat_nprobe_1_Sara_v2_v2.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb92072faf8c51974955adfc9bf1df62d51c65be46c080253a81a5b24e08cbc
3
+ size 31588619
Sara_v2/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": {
3
+ "filter_length": 2048,
4
+ "hop_length": 400,
5
+ "max_wav_value": 32768.0,
6
+ "mel_fmax": null,
7
+ "mel_fmin": 0.0,
8
+ "n_mel_channels": 125,
9
+ "sampling_rate": 40000,
10
+ "win_length": 2048
11
+ },
12
+ "model": {
13
+ "filter_channels": 768,
14
+ "gin_channels": 256,
15
+ "hidden_channels": 192,
16
+ "inter_channels": 192,
17
+ "kernel_size": 3,
18
+ "n_heads": 2,
19
+ "n_layers": 6,
20
+ "p_dropout": 0,
21
+ "resblock": "1",
22
+ "resblock_dilation_sizes": [
23
+ [
24
+ 1,
25
+ 3,
26
+ 5
27
+ ],
28
+ [
29
+ 1,
30
+ 3,
31
+ 5
32
+ ],
33
+ [
34
+ 1,
35
+ 3,
36
+ 5
37
+ ]
38
+ ],
39
+ "resblock_kernel_sizes": [
40
+ 3,
41
+ 7,
42
+ 11
43
+ ],
44
+ "spk_embed_dim": 109,
45
+ "upsample_initial_channel": 512,
46
+ "upsample_kernel_sizes": [
47
+ 16,
48
+ 16,
49
+ 4,
50
+ 4
51
+ ],
52
+ "upsample_rates": [
53
+ 10,
54
+ 10,
55
+ 2,
56
+ 2
57
+ ],
58
+ "use_spectral_norm": false
59
+ },
60
+ "train": {
61
+ "batch_size": 4,
62
+ "betas": [
63
+ 0.8,
64
+ 0.99
65
+ ],
66
+ "c_kl": 1.0,
67
+ "c_mel": 45,
68
+ "epochs": 20000,
69
+ "eps": 1e-09,
70
+ "fp16_run": true,
71
+ "init_lr_ratio": 1,
72
+ "learning_rate": 0.0001,
73
+ "log_interval": 200,
74
+ "lr_decay": 0.999875,
75
+ "seed": 1234,
76
+ "segment_size": 12800,
77
+ "warmup_epochs": 0
78
+ }
79
+ }