add files for sovits models
Browse files- 00_08_09_10_11_12_13_14_15_16_25_26/G_64000.pth +3 -0
- 00_08_09_10_11_12_13_14_15_16_25_26/config.json +104 -0
- 01_02/G_64000.pth +3 -0
- 01_02/config.json +94 -0
- kmeans_10000.pt → 01_02/kmeans_10000.pt +2 -2
- 03_07_22_23_24/G_40000.pth +3 -0
- 03_07_22_23_24/config.json +97 -0
- 03_07_22_23_24/kmeans_10000.pt +3 -0
- 04_05/G_52000.pth +3 -0
- 04_05/config.json +94 -0
- 04_05/kmeans_10000.pt +3 -0
- G_61000.pth → 06_21_27_28/G_61000.pth +0 -0
- 06_21_27_28/config.json +96 -0
- 06_21_27_28/kmeans_10000.pt +3 -0
- 角色编号列表.txt +27 -0
00_08_09_10_11_12_13_14_15_16_25_26/G_64000.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9dd540249a934e841f3487479f4bd93513368dac4022869b1c6a16eba27a676
|
| 3 |
+
size 542789405
|
00_08_09_10_11_12_13_14_15_16_25_26/config.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 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": 6
|
| 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 |
+
"Shido": 0,
|
| 92 |
+
"Reine": 1,
|
| 93 |
+
"Kannazuki": 2,
|
| 94 |
+
"Tonomachi": 3,
|
| 95 |
+
"Tamae": 4,
|
| 96 |
+
"Kusakabe": 5,
|
| 97 |
+
"Ai": 6,
|
| 98 |
+
"Mai": 7,
|
| 99 |
+
"Mii": 8,
|
| 100 |
+
"Ruler": 9,
|
| 101 |
+
"Mana": 10,
|
| 102 |
+
"Mikie": 11
|
| 103 |
+
}
|
| 104 |
+
}
|
01_02/G_64000.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf377813b9710b52ba60f3c6525aa2502295e90771b3c622a6c91a6bb188315d
|
| 3 |
+
size 542789405
|
01_02/config.json
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"Tohka": 0,
|
| 92 |
+
"Origami": 1
|
| 93 |
+
}
|
| 94 |
+
}
|
kmeans_10000.pt → 01_02/kmeans_10000.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ee8383018458a6b1f051e7ab65ce078aa95c35cce221b443f4e87df730aa934
|
| 3 |
+
size 30852409
|
03_07_22_23_24/G_40000.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:768063c4023f77bc9065a05a8e9cdf9c354bfb3a6d4a4c26398982d74adbc62d
|
| 3 |
+
size 542789405
|
03_07_22_23_24/config.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 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": 6
|
| 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 |
+
"Yoshino": 0,
|
| 92 |
+
"Yoshinon": 1,
|
| 93 |
+
"Kaguya": 2,
|
| 94 |
+
"Yuzuru": 3,
|
| 95 |
+
"Miku": 4
|
| 96 |
+
}
|
| 97 |
+
}
|
03_07_22_23_24/kmeans_10000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc053b46659c3c42b1332d029cc9af9d928c717b0a880dd65cd107a6d7f2fb81
|
| 3 |
+
size 77134585
|
04_05/G_52000.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff5624a237ecabc532d9eab7c7de5509bbb870081076b78c5b6a7ac639e26416
|
| 3 |
+
size 542789405
|
04_05/config.json
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 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": 6
|
| 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 |
+
"Kurumi": 0,
|
| 92 |
+
"Kotori": 1
|
| 93 |
+
}
|
| 94 |
+
}
|
04_05/kmeans_10000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6bb0fc10989737e7708adab4ce569472a23958acc74f31c9ed73f8467abf36f
|
| 3 |
+
size 30849081
|
G_61000.pth → 06_21_27_28/G_61000.pth
RENAMED
|
File without changes
|
06_21_27_28/config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"Rinne": 0,
|
| 92 |
+
"Marina": 1,
|
| 93 |
+
"Rio": 2,
|
| 94 |
+
"Maria": 3
|
| 95 |
+
}
|
| 96 |
+
}
|
06_21_27_28/kmeans_10000.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08321d51281cfd7534f2dfd8d7cef902da73999a03d08311578bc8bf3c616b60
|
| 3 |
+
size 61727033
|
角色编号列表.txt
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
00 士道
|
| 2 |
+
01 十香
|
| 3 |
+
02 折纸
|
| 4 |
+
03 四糸乃
|
| 5 |
+
04 狂三
|
| 6 |
+
05 琴里
|
| 7 |
+
06 凛祢
|
| 8 |
+
07 四糸奈
|
| 9 |
+
08 令音
|
| 10 |
+
09 神无月
|
| 11 |
+
10 殿町
|
| 12 |
+
11 珠惠
|
| 13 |
+
12 燎子
|
| 14 |
+
13 亚衣
|
| 15 |
+
14 麻衣
|
| 16 |
+
15 美衣
|
| 17 |
+
16 支配者
|
| 18 |
+
17 守护者
|
| 19 |
+
21 鞠亚
|
| 20 |
+
22 耶俱矢
|
| 21 |
+
23 夕弦
|
| 22 |
+
24 美九
|
| 23 |
+
25 真那
|
| 24 |
+
26 美纪惠
|
| 25 |
+
27 鞠奈
|
| 26 |
+
28 凛绪
|
| 27 |
+
99 澪
|