Hugging Face's logo

437aewuh
/
so-vits-svc-fork-kiritan

Audio-to-Audio
TensorBoard
Japanese
music
Model card Files Metrics Community
10
34j commited on
Commit
15db490
•
1 Parent(s): 55086f1

feat: add models

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. mb-istft-256-44k/.ipynb_checkpoints/config-checkpoint.json +107 -0
  2. mb-istft-256-44k/D_5600.pth +3 -0
  3. mb-istft-256-44k/G_5600.pth +3 -0
  4. mb-istft-256-44k/config.json +107 -0
  5. mb-istft-256-44k/eval/events.out.tfevents.1680340190.n8x232yzmw.713.1 +3 -0
  6. mb-istft-256-44k/eval/events.out.tfevents.1680340606.n8x232yzmw.1030.1 +3 -0
  7. mb-istft-256-44k/eval/events.out.tfevents.1680340755.n8x232yzmw.1666.1 +3 -0
  8. mb-istft-256-44k/eval/events.out.tfevents.1680340780.n8x232yzmw.1899.1 +3 -0
  9. mb-istft-256-44k/eval/events.out.tfevents.1680343331.nc8685wj3u.327.1 +3 -0
  10. mb-istft-256-44k/eval/events.out.tfevents.1680344075.nsf2h8cusz.309.1 +3 -0
  11. mb-istft-256-44k/eval/events.out.tfevents.1680346225.nrrvlcfi7n.373.1 +3 -0
  12. mb-istft-256-44k/eval/events.out.tfevents.1680346313.nrrvlcfi7n.566.1 +3 -0
  13. mb-istft-256-44k/events.out.tfevents.1680340190.n8x232yzmw.713.0 +3 -0
  14. mb-istft-256-44k/events.out.tfevents.1680340606.n8x232yzmw.1030.0 +3 -0
  15. mb-istft-256-44k/events.out.tfevents.1680340755.n8x232yzmw.1666.0 +3 -0
  16. mb-istft-256-44k/events.out.tfevents.1680340780.n8x232yzmw.1899.0 +3 -0
  17. mb-istft-256-44k/events.out.tfevents.1680343331.nc8685wj3u.327.0 +3 -0
  18. mb-istft-256-44k/events.out.tfevents.1680344075.nsf2h8cusz.309.0 +3 -0
  19. mb-istft-256-44k/events.out.tfevents.1680346225.nrrvlcfi7n.373.0 +3 -0
  20. mb-istft-256-44k/events.out.tfevents.1680346313.nrrvlcfi7n.566.0 +3 -0
  21. ms-istft-256-44k/.ipynb_checkpoints/config-checkpoint.json +107 -0
  22. ms-istft-256-44k/D_36400.pth +3 -0
  23. ms-istft-256-44k/G_36400.pth +3 -0
  24. ms-istft-256-44k/config.json +107 -0
  25. ms-istft-256-44k/eval/events.out.tfevents.1680360112.ngr33j4f2i.348.1 +3 -0
  26. ms-istft-256-44k/eval/events.out.tfevents.1680361002.ngr33j4f2i.4845.1 +3 -0
  27. ms-istft-256-44k/eval/events.out.tfevents.1680398464.ncfvompi0o.325.1 +3 -0
  28. ms-istft-256-44k/events.out.tfevents.1680360112.ngr33j4f2i.348.0 +3 -0
  29. ms-istft-256-44k/events.out.tfevents.1680361002.ngr33j4f2i.4845.0 +3 -0
  30. ms-istft-256-44k/events.out.tfevents.1680398464.ncfvompi0o.325.0 +3 -0
  31. ms-istft-768-44k/.ipynb_checkpoints/config-checkpoint.json +108 -0
  32. ms-istft-768-44k/D_15200.pth +3 -0
  33. ms-istft-768-44k/G_15200.pth +3 -0
  34. ms-istft-768-44k/config.json +108 -0
  35. ms-istft-768-44k/eval/events.out.tfevents.1680490970.nuu0tnekj3.1132.1 +3 -0
  36. ms-istft-768-44k/eval/events.out.tfevents.1680509615.nuu0tnekj3.27348.1 +3 -0
  37. ms-istft-768-44k/eval/events.out.tfevents.1680526176.nsc4fp4ef8.383.1 +3 -0
  38. ms-istft-768-44k/eval/events.out.tfevents.1680530794.nsc4fp4ef8.21066.1 +3 -0
  39. ms-istft-768-44k/eval/events.out.tfevents.1680531004.nsc4fp4ef8.21163.1 +3 -0
  40. ms-istft-768-44k/eval/events.out.tfevents.1680531054.nsc4fp4ef8.21224.1 +3 -0
  41. ms-istft-768-44k/eval/events.out.tfevents.1680531129.nsc4fp4ef8.21285.1 +3 -0
  42. ms-istft-768-44k/eval/events.out.tfevents.1680531150.nsc4fp4ef8.21346.1 +3 -0
  43. ms-istft-768-44k/eval/events.out.tfevents.1680531819.nsc4fp4ef8.21448.1 +3 -0
  44. ms-istft-768-44k/eval/events.out.tfevents.1680531901.nsc4fp4ef8.21509.1 +3 -0
  45. ms-istft-768-44k/eval/events.out.tfevents.1680531966.nsc4fp4ef8.21607.1 +3 -0
  46. ms-istft-768-44k/eval/events.out.tfevents.1680532012.nsc4fp4ef8.21668.1 +3 -0
  47. ms-istft-768-44k/eval/events.out.tfevents.1680532158.nsc4fp4ef8.21766.1 +3 -0
  48. ms-istft-768-44k/eval/events.out.tfevents.1680532431.nsc4fp4ef8.21966.1 +3 -0
  49. ms-istft-768-44k/eval/events.out.tfevents.1680532563.nsc4fp4ef8.22075.1 +3 -0
  50. ms-istft-768-44k/eval/events.out.tfevents.1680533096.nsc4fp4ef8.22335.1 +3 -0
mb-istft-256-44k/.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "eval_interval": 800,
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
+ "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
+ "fft_sizes": [
26
+ 384,
27
+ 683,
28
+ 171
29
+ ],
30
+ "hop_sizes": [
31
+ 30,
32
+ 60,
33
+ 10
34
+ ],
35
+ "win_lengths": [
36
+ 150,
37
+ 300,
38
+ 60
39
+ ],
40
+ "window": "hann_window"
41
+ },
42
+ "data": {
43
+ "training_files": "filelists/44k/train.txt",
44
+ "validation_files": "filelists/44k/val.txt",
45
+ "max_wav_value": 32768.0,
46
+ "sampling_rate": 44100,
47
+ "filter_length": 2048,
48
+ "hop_length": 512,
49
+ "win_length": 2048,
50
+ "n_mel_channels": 80,
51
+ "mel_fmin": 0.0,
52
+ "mel_fmax": 22050
53
+ },
54
+ "model": {
55
+ "inter_channels": 192,
56
+ "hidden_channels": 192,
57
+ "filter_channels": 768,
58
+ "n_heads": 2,
59
+ "n_layers": 6,
60
+ "kernel_size": 3,
61
+ "p_dropout": 0.1,
62
+ "resblock": "1",
63
+ "resblock_kernel_sizes": [
64
+ 3,
65
+ 7,
66
+ 11
67
+ ],
68
+ "resblock_dilation_sizes": [
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ],
74
+ [
75
+ 1,
76
+ 3,
77
+ 5
78
+ ],
79
+ [
80
+ 1,
81
+ 3,
82
+ 5
83
+ ]
84
+ ],
85
+ "upsample_rates": [
86
+ 4,
87
+ 4
88
+ ],
89
+ "upsample_initial_channel": 512,
90
+ "upsample_kernel_sizes": [
91
+ 16,
92
+ 16
93
+ ],
94
+ "n_layers_q": 3,
95
+ "use_spectral_norm": false,
96
+ "gin_channels": 256,
97
+ "ssl_dim": 256,
98
+ "n_speakers": 200,
99
+ "type_": "mb-istft",
100
+ "gen_istft_n_fft": 16,
101
+ "gen_istft_hop_size": 4,
102
+ "subbands": 8
103
+ },
104
+ "spk": {
105
+ "kiritan": 0
106
+ }
107
+ }
mb-istft-256-44k/D_5600.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48bde3e10dadaa937a9f22de4e50374e8fae2995c97f97114113ffe3d903e1c7
3
+ size 561098185
mb-istft-256-44k/G_5600.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9925fa77bc6cccf079d9fab4677877950930c8dfa6d07131af95b984e09551cb
3
+ size 533410689
mb-istft-256-44k/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 50,
4
+ "eval_interval": 800,
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": 19,
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
+ "fft_sizes": [
26
+ 384,
27
+ 683,
28
+ 171
29
+ ],
30
+ "hop_sizes": [
31
+ 30,
32
+ 60,
33
+ 10
34
+ ],
35
+ "win_lengths": [
36
+ 150,
37
+ 300,
38
+ 60
39
+ ],
40
+ "window": "hann_window"
41
+ },
42
+ "data": {
43
+ "training_files": "filelists/44k/train.txt",
44
+ "validation_files": "filelists/44k/val.txt",
45
+ "max_wav_value": 32768.0,
46
+ "sampling_rate": 44100,
47
+ "filter_length": 2048,
48
+ "hop_length": 512,
49
+ "win_length": 2048,
50
+ "n_mel_channels": 80,
51
+ "mel_fmin": 0.0,
52
+ "mel_fmax": 22050
53
+ },
54
+ "model": {
55
+ "inter_channels": 192,
56
+ "hidden_channels": 192,
57
+ "filter_channels": 768,
58
+ "n_heads": 2,
59
+ "n_layers": 6,
60
+ "kernel_size": 3,
61
+ "p_dropout": 0.1,
62
+ "resblock": "1",
63
+ "resblock_kernel_sizes": [
64
+ 3,
65
+ 7,
66
+ 11
67
+ ],
68
+ "resblock_dilation_sizes": [
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ],
74
+ [
75
+ 1,
76
+ 3,
77
+ 5
78
+ ],
79
+ [
80
+ 1,
81
+ 3,
82
+ 5
83
+ ]
84
+ ],
85
+ "upsample_rates": [
86
+ 4,
87
+ 4
88
+ ],
89
+ "upsample_initial_channel": 512,
90
+ "upsample_kernel_sizes": [
91
+ 16,
92
+ 16
93
+ ],
94
+ "n_layers_q": 3,
95
+ "use_spectral_norm": false,
96
+ "gin_channels": 256,
97
+ "ssl_dim": 256,
98
+ "n_speakers": 200,
99
+ "type_": "mb-istft",
100
+ "gen_istft_n_fft": 16,
101
+ "gen_istft_hop_size": 4,
102
+ "subbands": 8
103
+ },
104
+ "spk": {
105
+ "kiritan": 0
106
+ }
107
+ }
mb-istft-256-44k/eval/events.out.tfevents.1680340190.n8x232yzmw.713.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b5d7e46adffeac22ce8607fc62878de23821b762a14640d9992800d06f6323
3
+ size 88
mb-istft-256-44k/eval/events.out.tfevents.1680340606.n8x232yzmw.1030.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc36b71a8a916c0214a3616de97c8348012259b7477a306461851d5c21053194
3
+ size 1220696
mb-istft-256-44k/eval/events.out.tfevents.1680340755.n8x232yzmw.1666.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:316ad5a5e92c2692234d3e9c1db0cec65d969b6b1bfeb5fa930653368d20b7c2
3
+ size 1220696
mb-istft-256-44k/eval/events.out.tfevents.1680340780.n8x232yzmw.1899.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ceb78d54e9d332da9e965a33891c8544b5c0c5a4335794ad9280400af8de37
3
+ size 4844868
mb-istft-256-44k/eval/events.out.tfevents.1680343331.nc8685wj3u.327.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:316d5ca41cc3791a6688cbae5d295e5c812a46d146af0e93ceea5bed288e43e1
3
+ size 1206733
mb-istft-256-44k/eval/events.out.tfevents.1680344075.nsf2h8cusz.309.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f706953ae985b4b59b8ecc009febed5ab47c589551a70dc0a56e6266596d593
3
+ size 1204638
mb-istft-256-44k/eval/events.out.tfevents.1680346225.nrrvlcfi7n.373.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb40ffef3fcd5bea91c91b2a5d1142f154421d52c6dd8acae06946186a392d1
3
+ size 88
mb-istft-256-44k/eval/events.out.tfevents.1680346313.nrrvlcfi7n.566.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466dceb8d345b0c90ec761735d51e484aac87ebf3d374b2eb28b991a5be0ba9f
3
+ size 7230098
mb-istft-256-44k/events.out.tfevents.1680340190.n8x232yzmw.713.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a31637039986cdf2c57bd9699823fde22e6045d8cb528ad0836176f9c5a02c
3
+ size 88
mb-istft-256-44k/events.out.tfevents.1680340606.n8x232yzmw.1030.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668d7611dffec4b08f16ef3a449f3eab3f3f358e87c0d57447d583649532055b
3
+ size 262232
mb-istft-256-44k/events.out.tfevents.1680340755.n8x232yzmw.1666.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672f99b662c2fc3ca31186fcb7a7329af8247a906b79e998d79fe8f9c88fdd2b
3
+ size 90200
mb-istft-256-44k/events.out.tfevents.1680340780.n8x232yzmw.1899.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a071f403038af2adf6346c98ad75fd01314341e9c46ddb2703725b514baa5c0f
3
+ size 2376178
mb-istft-256-44k/events.out.tfevents.1680343331.nc8685wj3u.327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9a6967c2cedbb6b0389ad250ab25b9fa2f3cb5f39bf2bd44322d463ab0e0bd
3
+ size 344750
mb-istft-256-44k/events.out.tfevents.1680344075.nsf2h8cusz.309.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bbc75c02d46f4f5e0b5a7e2825ba43dccdf2cc969bc3e6f3b0e6384390863a6
3
+ size 745519
mb-istft-256-44k/events.out.tfevents.1680346225.nrrvlcfi7n.373.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea49a5598d31bfe598746937a5a70673951191579ef125b5099090d38d94fd0
3
+ size 88
mb-istft-256-44k/events.out.tfevents.1680346313.nrrvlcfi7n.566.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56aef6707ab048e13617478789780c219eaf8ff45e3983417fd9d2dfb87815a
3
+ size 18344089
ms-istft-256-44k/.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 50,
4
+ "eval_interval": 100,
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
+ "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
+ "fft_sizes": [
26
+ 384,
27
+ 683,
28
+ 171
29
+ ],
30
+ "hop_sizes": [
31
+ 30,
32
+ 60,
33
+ 10
34
+ ],
35
+ "win_lengths": [
36
+ 150,
37
+ 300,
38
+ 60
39
+ ],
40
+ "window": "hann_window"
41
+ },
42
+ "data": {
43
+ "training_files": "filelists/44k/train.txt",
44
+ "validation_files": "filelists/44k/val.txt",
45
+ "max_wav_value": 32768.0,
46
+ "sampling_rate": 44100,
47
+ "filter_length": 2048,
48
+ "hop_length": 512,
49
+ "win_length": 2048,
50
+ "n_mel_channels": 80,
51
+ "mel_fmin": 0.0,
52
+ "mel_fmax": 22050
53
+ },
54
+ "model": {
55
+ "inter_channels": 192,
56
+ "hidden_channels": 192,
57
+ "filter_channels": 768,
58
+ "n_heads": 2,
59
+ "n_layers": 6,
60
+ "kernel_size": 3,
61
+ "p_dropout": 0.1,
62
+ "resblock": "1",
63
+ "resblock_kernel_sizes": [
64
+ 3,
65
+ 7,
66
+ 11
67
+ ],
68
+ "resblock_dilation_sizes": [
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ],
74
+ [
75
+ 1,
76
+ 3,
77
+ 5
78
+ ],
79
+ [
80
+ 1,
81
+ 3,
82
+ 5
83
+ ]
84
+ ],
85
+ "upsample_rates": [
86
+ 4,
87
+ 4
88
+ ],
89
+ "upsample_initial_channel": 512,
90
+ "upsample_kernel_sizes": [
91
+ 16,
92
+ 16
93
+ ],
94
+ "n_layers_q": 3,
95
+ "use_spectral_norm": false,
96
+ "gin_channels": 256,
97
+ "ssl_dim": 256,
98
+ "n_speakers": 200,
99
+ "type_": "ms-istft",
100
+ "gen_istft_n_fft": 16,
101
+ "gen_istft_hop_size": 4,
102
+ "subbands": 8
103
+ },
104
+ "spk": {
105
+ "kiritan": 0
106
+ }
107
+ }
ms-istft-256-44k/D_36400.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa577dc75e46235d2c4b0d68cda9070df7659069742784e8401379825be51d1d
3
+ size 561098185
ms-istft-256-44k/G_36400.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ecd89776700f143b0deb9e496eaa41275e4a56b87716c04029cdd27c746f286
3
+ size 533421432
ms-istft-256-44k/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 50,
4
+ "eval_interval": 100,
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
+ "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
+ "fft_sizes": [
26
+ 384,
27
+ 683,
28
+ 171
29
+ ],
30
+ "hop_sizes": [
31
+ 30,
32
+ 60,
33
+ 10
34
+ ],
35
+ "win_lengths": [
36
+ 150,
37
+ 300,
38
+ 60
39
+ ],
40
+ "window": "hann_window"
41
+ },
42
+ "data": {
43
+ "training_files": "filelists/44k/train.txt",
44
+ "validation_files": "filelists/44k/val.txt",
45
+ "max_wav_value": 32768.0,
46
+ "sampling_rate": 44100,
47
+ "filter_length": 2048,
48
+ "hop_length": 512,
49
+ "win_length": 2048,
50
+ "n_mel_channels": 80,
51
+ "mel_fmin": 0.0,
52
+ "mel_fmax": 22050
53
+ },
54
+ "model": {
55
+ "inter_channels": 192,
56
+ "hidden_channels": 192,
57
+ "filter_channels": 768,
58
+ "n_heads": 2,
59
+ "n_layers": 6,
60
+ "kernel_size": 3,
61
+ "p_dropout": 0.1,
62
+ "resblock": "1",
63
+ "resblock_kernel_sizes": [
64
+ 3,
65
+ 7,
66
+ 11
67
+ ],
68
+ "resblock_dilation_sizes": [
69
+ [
70
+ 1,
71
+ 3,
72
+ 5
73
+ ],
74
+ [
75
+ 1,
76
+ 3,
77
+ 5
78
+ ],
79
+ [
80
+ 1,
81
+ 3,
82
+ 5
83
+ ]
84
+ ],
85
+ "upsample_rates": [
86
+ 4,
87
+ 4
88
+ ],
89
+ "upsample_initial_channel": 512,
90
+ "upsample_kernel_sizes": [
91
+ 16,
92
+ 16
93
+ ],
94
+ "n_layers_q": 3,
95
+ "use_spectral_norm": false,
96
+ "gin_channels": 256,
97
+ "ssl_dim": 256,
98
+ "n_speakers": 200,
99
+ "type_": "ms-istft",
100
+ "gen_istft_n_fft": 16,
101
+ "gen_istft_hop_size": 4,
102
+ "subbands": 8
103
+ },
104
+ "spk": {
105
+ "kiritan": 0
106
+ }
107
+ }
ms-istft-256-44k/eval/events.out.tfevents.1680360112.ngr33j4f2i.348.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554514823eb3721bfeb5b1cac1ccdcc25d26692b3d09a1e8d25f982830d63f1e
3
+ size 3649056
ms-istft-256-44k/eval/events.out.tfevents.1680361002.ngr33j4f2i.4845.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c287fd3d23fe658512d8178fda6391aef7c5e3acb8f6520ac58205f39e70369d
3
+ size 217836704
ms-istft-256-44k/eval/events.out.tfevents.1680398464.ncfvompi0o.325.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa04ff151fc917f736f844a96e1ea47b018351f89b64057bfbc106ed0d6a71d6
3
+ size 219034927
ms-istft-256-44k/events.out.tfevents.1680360112.ngr33j4f2i.348.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39297f21addda91578f0f8bded92f52f2c55b17057f18d84f81a3b391d8aa899
3
+ size 1023540
ms-istft-256-44k/events.out.tfevents.1680361002.ngr33j4f2i.4845.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ec69dda44188ce7f9f684d26b99b4ed5d440bc12bf1615c0ca3c0430084722
3
+ size 68554768
ms-istft-256-44k/events.out.tfevents.1680398464.ncfvompi0o.325.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91cfa0efe7d121f5b21e9a97f639a0b0f691e40facc5bac503f14857ad3bef4d
3
+ size 67567770
ms-istft-768-44k/.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 18,
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
+ "fft_sizes": [
26
+ 768,
27
+ 1366,
28
+ 342
29
+ ],
30
+ "hop_sizes": [
31
+ 60,
32
+ 120,
33
+ 20
34
+ ],
35
+ "win_lengths": [
36
+ 300,
37
+ 600,
38
+ 120
39
+ ],
40
+ "window": "hann_window"
41
+ },
42
+ "data": {
43
+ "training_files": "filelists/44k/train.txt",
44
+ "validation_files": "filelists/44k/val.txt",
45
+ "max_wav_value": 32768.0,
46
+ "sampling_rate": 44100,
47
+ "filter_length": 2048,
48
+ "hop_length": 512,
49
+ "win_length": 2048,
50
+ "n_mel_channels": 80,
51
+ "mel_fmin": 0.0,
52
+ "mel_fmax": 22050,
53
+ "contentvec_final_proj": false
54
+ },
55
+ "model": {
56
+ "inter_channels": 192,
57
+ "hidden_channels": 192,
58
+ "filter_channels": 768,
59
+ "n_heads": 2,
60
+ "n_layers": 6,
61
+ "kernel_size": 3,
62
+ "p_dropout": 0.1,
63
+ "resblock": "1",
64
+ "resblock_kernel_sizes": [
65
+ 3,
66
+ 7,
67
+ 11
68
+ ],
69
+ "resblock_dilation_sizes": [
70
+ [
71
+ 1,
72
+ 3,
73
+ 5
74
+ ],
75
+ [
76
+ 1,
77
+ 3,
78
+ 5
79
+ ],
80
+ [
81
+ 1,
82
+ 3,
83
+ 5
84
+ ]
85
+ ],
86
+ "upsample_rates": [
87
+ 8,
88
+ 4
89
+ ],
90
+ "upsample_initial_channel": 512,
91
+ "upsample_kernel_sizes": [
92
+ 32,
93
+ 16
94
+ ],
95
+ "n_layers_q": 3,
96
+ "use_spectral_norm": false,
97
+ "gin_channels": 256,
98
+ "ssl_dim": 768,
99
+ "n_speakers": 200,
100
+ "type_": "ms-istft",
101
+ "gen_istft_n_fft": 16,
102
+ "gen_istft_hop_size": 4,
103
+ "subbands": 4
104
+ },
105
+ "spk": {
106
+ "kiritan": 0
107
+ }
108
+ }
ms-istft-768-44k/D_15200.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3da3fffed402a50f07b76d498948b1bc6c64aa0663d8c9bdf47c47b893a54a
3
+ size 561098185
ms-istft-768-44k/G_15200.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fe6ab0c8bd1b7e4e9e2450b157175e3e7457b3efb550b77a5ca33017182015
3
+ size 563704568
ms-istft-768-44k/config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 18,
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
+ "fft_sizes": [
26
+ 768,
27
+ 1366,
28
+ 342
29
+ ],
30
+ "hop_sizes": [
31
+ 60,
32
+ 120,
33
+ 20
34
+ ],
35
+ "win_lengths": [
36
+ 300,
37
+ 600,
38
+ 120
39
+ ],
40
+ "window": "hann_window"
41
+ },
42
+ "data": {
43
+ "training_files": "filelists/44k/train.txt",
44
+ "validation_files": "filelists/44k/val.txt",
45
+ "max_wav_value": 32768.0,
46
+ "sampling_rate": 44100,
47
+ "filter_length": 2048,
48
+ "hop_length": 512,
49
+ "win_length": 2048,
50
+ "n_mel_channels": 80,
51
+ "mel_fmin": 0.0,
52
+ "mel_fmax": 22050,
53
+ "contentvec_final_proj": false
54
+ },
55
+ "model": {
56
+ "inter_channels": 192,
57
+ "hidden_channels": 192,
58
+ "filter_channels": 768,
59
+ "n_heads": 2,
60
+ "n_layers": 6,
61
+ "kernel_size": 3,
62
+ "p_dropout": 0.1,
63
+ "resblock": "1",
64
+ "resblock_kernel_sizes": [
65
+ 3,
66
+ 7,
67
+ 11
68
+ ],
69
+ "resblock_dilation_sizes": [
70
+ [
71
+ 1,
72
+ 3,
73
+ 5
74
+ ],
75
+ [
76
+ 1,
77
+ 3,
78
+ 5
79
+ ],
80
+ [
81
+ 1,
82
+ 3,
83
+ 5
84
+ ]
85
+ ],
86
+ "upsample_rates": [
87
+ 8,
88
+ 4
89
+ ],
90
+ "upsample_initial_channel": 512,
91
+ "upsample_kernel_sizes": [
92
+ 32,
93
+ 16
94
+ ],
95
+ "n_layers_q": 3,
96
+ "use_spectral_norm": false,
97
+ "gin_channels": 256,
98
+ "ssl_dim": 768,
99
+ "n_speakers": 200,
100
+ "type_": "ms-istft",
101
+ "gen_istft_n_fft": 16,
102
+ "gen_istft_hop_size": 4,
103
+ "subbands": 4
104
+ },
105
+ "spk": {
106
+ "kiritan": 0
107
+ }
108
+ }
ms-istft-768-44k/eval/events.out.tfevents.1680490970.nuu0tnekj3.1132.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:517c03ab328eda0ed847049e7fbc5b0d20e47bcc5538d2dabc4e034e25afabf3
3
+ size 144331787
ms-istft-768-44k/eval/events.out.tfevents.1680509615.nuu0tnekj3.27348.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bff6c4380109a5be67602544b66c828b078a9845f363a41eb8818954b45da21
3
+ size 21006064
ms-istft-768-44k/eval/events.out.tfevents.1680526176.nsc4fp4ef8.383.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6316d7e805d5f7ac71c55833a9c71cab0bf102e32c26f634a37d828038d93262
3
+ size 42028670
ms-istft-768-44k/eval/events.out.tfevents.1680530794.nsc4fp4ef8.21066.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f998c140d511df2531a6c99b11b7e8c02c9b19a7d49d6acbe554e9b3ab571f
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680531004.nsc4fp4ef8.21163.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb061228ef7281ce34bf474f9e945673d28fef5f124e3618184601336f8bd1aa
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680531054.nsc4fp4ef8.21224.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f833337e2bae319ea0c8073d20f28dd2053aeddbb36bee0db04b48c68d992403
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680531129.nsc4fp4ef8.21285.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa178712892adc4502cced260f8b291c8604eb0e9ab8f1b28c535511cb33d5f
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680531150.nsc4fp4ef8.21346.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d707a9212351e69f8fe926b2bc0ee372515611d1eee0ffb65c19e68cf9ccbeb
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680531819.nsc4fp4ef8.21448.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb00414b265020634b7002c36c89b391bf2fd22912f816e7daaca916c43dc43e
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680531901.nsc4fp4ef8.21509.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1588f3ce3b27e2c1d8823f6b1973f77413ef3ec64f6d3736ff2a6d57288d72fe
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680531966.nsc4fp4ef8.21607.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96aeef429ad2b5a9bcb5538757fe60b1d13f79a572ca0e05cdb74a632098ec38
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680532012.nsc4fp4ef8.21668.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad826f629ed4c815bd08b0f1ff4495d2ea73b521f54f43064779f2d820312b0
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680532158.nsc4fp4ef8.21766.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b5acde0092c1685de8baf620f2ccd392c05cd115fd3457440b2a197694bfb1
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680532431.nsc4fp4ef8.21966.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7659268150b091dcf062a83c53a3ca16c8b3b56b3c60316f6899e57d07f378e
3
+ size 88
ms-istft-768-44k/eval/events.out.tfevents.1680532563.nsc4fp4ef8.22075.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddab8b258f47a7eb3bc9d8a10d718d2746aa83f63c6ffdec21efb5bc4736c5da
3
+ size 180230311
ms-istft-768-44k/eval/events.out.tfevents.1680533096.nsc4fp4ef8.22335.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caa110ca5fdeb2948a2a2c9d32a2924b588e188d722ce652b868ba5bd7c13ac0
3
+ size 2628718