Delete so_vits_svc_4
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- so_vits_svc_4/Apple Bloom (singing, PS1)/speaker.json +0 -3
- so_vits_svc_4/Applejack (singing, PS1)/speaker.json +0 -3
- so_vits_svc_4/Babs Seed (alt)/speaker.json +0 -3
- so_vits_svc_4/Babs Seed/G_1668.pth +0 -3
- so_vits_svc_4/Babs Seed/README.txt +0 -4
- so_vits_svc_4/Babs Seed/config.json +0 -104
- so_vits_svc_4/Babs Seed/kmeans.pt +0 -3
- so_vits_svc_4/Big McIntosh/G_1668.pth +0 -3
- so_vits_svc_4/Big McIntosh/README.txt +0 -4
- so_vits_svc_4/Big McIntosh/config.json +0 -105
- so_vits_svc_4/Big McIntosh/kmeans.pt +0 -3
- so_vits_svc_4/Big McIntosh/speaker.json +0 -3
- so_vits_svc_4/Braeburn/G_1668.pth +0 -3
- so_vits_svc_4/Braeburn/README.txt +0 -4
- so_vits_svc_4/Braeburn/config.json +0 -104
- so_vits_svc_4/Braeburn/kmeans.pt +0 -3
- so_vits_svc_4/Cadance (singing, PS1)/speaker.json +0 -3
- so_vits_svc_4/Celestia (singing)/speaker.json +0 -3
- so_vits_svc_4/Celestia (singing, PS1)/speaker.json +0 -3
- so_vits_svc_4/Celestia (singing, alt)/speaker.json +0 -3
- so_vits_svc_4/Daring Do/speaker.json +0 -3
- so_vits_svc_4/Diamond Tiara/G_6000.pth +0 -3
- so_vits_svc_4/Diamond Tiara/README.txt +0 -4
- so_vits_svc_4/Diamond Tiara/config.json +0 -98
- so_vits_svc_4/Diamond Tiara/kmeans.pt +0 -3
- so_vits_svc_4/Doctor Whooves/G_1668.pth +0 -3
- so_vits_svc_4/Doctor Whooves/README.txt +0 -4
- so_vits_svc_4/Doctor Whooves/config.json +0 -98
- so_vits_svc_4/Flam/speaker.json +0 -3
- so_vits_svc_4/Flim/speaker.json +0 -3
- so_vits_svc_4/Fluttershy (singing, PS1)/speaker.json +0 -3
- so_vits_svc_4/Gallus/G_10000.pth +0 -3
- so_vits_svc_4/Gallus/README.txt +0 -4
- so_vits_svc_4/Gallus/config.json +0 -98
- so_vits_svc_4/Lightning Dust/speaker.json +0 -3
- so_vits_svc_4/Luna (singing, PS1)/speaker.json +0 -3
- so_vits_svc_4/Moon Dancer/speaker.json +0 -3
- so_vits_svc_4/Ocellus/G_1668.pth +0 -3
- so_vits_svc_4/Ocellus/Readme.txt +0 -4
- so_vits_svc_4/Ocellus/config.json +0 -104
- so_vits_svc_4/Ocellus/kmeans.pt +0 -3
- so_vits_svc_4/Pinkie Pie (angry)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (annoyed)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (anxious)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (fearful)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (happy)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (neutral)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (nonverbal)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (sad shouting)/speaker.json +0 -3
- so_vits_svc_4/Pinkie Pie (sad)/speaker.json +0 -3
so_vits_svc_4/Apple Bloom (singing, PS1)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Applebloom (singing)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Applejack (singing, PS1)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Applejack (singing)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Babs Seed (alt)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Babs-Seed"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Babs Seed/G_1668.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:abd4211820f140813b9457b1443c0ca212c21e3c8a357b7c7446ec9620787f18
|
| 3 |
-
size 548687709
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Babs Seed/README.txt
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
Originally uploaded by ThunderAnon:
|
| 2 |
-
https://drive.google.com/drive/folders/1F0_Idv8G3s0R7RWxF_PctdxnAWUeyH_C?usp=sharing
|
| 3 |
-
Each zip and rar file in that link contained a large D_.pth file which is not needed for inference,
|
| 4 |
-
so I have reuploaded just the necessary files to the reduce the download time for Hay Say.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Babs Seed/config.json
DELETED
|
@@ -1,104 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"train": {
|
| 3 |
-
"log_interval": 100,
|
| 4 |
-
"eval_interval": 1000,
|
| 5 |
-
"seed": 1234,
|
| 6 |
-
"epochs": 1668,
|
| 7 |
-
"learning_rate": 0.0001,
|
| 8 |
-
"betas": [
|
| 9 |
-
0.8,
|
| 10 |
-
0.99
|
| 11 |
-
],
|
| 12 |
-
"eps": 1e-09,
|
| 13 |
-
"batch_size": 7,
|
| 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 |
-
"Babs-Seed": 0
|
| 103 |
-
}
|
| 104 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Babs Seed/kmeans.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d8db10039ba64c92555a340f6e2e0c1d8be4bb7365c7aa38996f4b0667915547
|
| 3 |
-
size 9243631
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Big McIntosh/G_1668.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d04c46333bc2218ab095237496fc9a868f46e723b1c964c7f567a9e66818c0ea
|
| 3 |
-
size 548687709
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Big McIntosh/README.txt
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
Originally uploaded by ThunderAnon:
|
| 2 |
-
https://drive.google.com/drive/folders/1F0_Idv8G3s0R7RWxF_PctdxnAWUeyH_C?usp=sharing
|
| 3 |
-
Each zip and rar file in that link contained a large D_.pth file which is not needed for inference,
|
| 4 |
-
so I have reuploaded just the necessary files to the reduce the download time for Hay Say.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Big McIntosh/config.json
DELETED
|
@@ -1,105 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"train": {
|
| 3 |
-
"log_interval": 100,
|
| 4 |
-
"eval_interval": 1000,
|
| 5 |
-
"seed": 1234,
|
| 6 |
-
"epochs": 1668,
|
| 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 |
-
"Babs-Seed": 0,
|
| 103 |
-
"Big-Mac": 1
|
| 104 |
-
}
|
| 105 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Big McIntosh/kmeans.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:56d36b19a77ec7fb8b6e008f62f64b1be3947cd34326b3728db10c3688e52636
|
| 3 |
-
size 18488879
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Big McIntosh/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Big-Mac"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Braeburn/G_1668.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:36483d802d182638f5994eae084367c67622e6fa957c6ba66491fd3f3f1cb45d
|
| 3 |
-
size 548687709
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Braeburn/README.txt
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
Originally uploaded by ThunderAnon:
|
| 2 |
-
https://drive.google.com/drive/folders/1F0_Idv8G3s0R7RWxF_PctdxnAWUeyH_C?usp=sharing
|
| 3 |
-
Each zip and rar file in that link contained a large D_.pth file which is not needed for inference,
|
| 4 |
-
so I have reuploaded just the necessary files to the reduce the download time for Hay Say.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Braeburn/config.json
DELETED
|
@@ -1,104 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"train": {
|
| 3 |
-
"log_interval": 100,
|
| 4 |
-
"eval_interval": 1000,
|
| 5 |
-
"seed": 1234,
|
| 6 |
-
"epochs": 1668,
|
| 7 |
-
"learning_rate": 0.0001,
|
| 8 |
-
"betas": [
|
| 9 |
-
0.8,
|
| 10 |
-
0.99
|
| 11 |
-
],
|
| 12 |
-
"eps": 1e-09,
|
| 13 |
-
"batch_size": 7,
|
| 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 |
-
"Braeburn": 0
|
| 103 |
-
}
|
| 104 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Braeburn/kmeans.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e0086d6d60dc45d6c6bf1803269ee2f847ad5e9eb38b855bdde54d633236f877
|
| 3 |
-
size 9239791
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Cadance (singing, PS1)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Cadance (singing)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Celestia (singing)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Celestia (singing)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Celestia (singing, PS1)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Celestia (singing)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Celestia (singing, alt)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Celestia (singing 2)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Daring Do/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "ddm_DaringDo"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Diamond Tiara/G_6000.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a545aaa00101ae937f0e9a9f6bbde4a47db057f53a28a28609753318781a844e
|
| 3 |
-
size 542789469
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Diamond Tiara/README.txt
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
Originally uploaded by ThunderAnon:
|
| 2 |
-
https://drive.google.com/drive/folders/1F0_Idv8G3s0R7RWxF_PctdxnAWUeyH_C?usp=sharing
|
| 3 |
-
Each zip and rar file in that link contained a large D_.pth file which is not needed for inference,
|
| 4 |
-
so I have reuploaded just the necessary files to the reduce the download time for Hay Say.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Diamond Tiara/config.json
DELETED
|
@@ -1,98 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"train": {
|
| 3 |
-
"log_interval": 200,
|
| 4 |
-
"eval_interval": 1000,
|
| 5 |
-
"seed": 1234,
|
| 6 |
-
"epochs": 6000,
|
| 7 |
-
"learning_rate": 0.0001,
|
| 8 |
-
"betas": [
|
| 9 |
-
0.8,
|
| 10 |
-
0.99
|
| 11 |
-
],
|
| 12 |
-
"eps": 1e-09,
|
| 13 |
-
"batch_size": 7,
|
| 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 |
-
},
|
| 43 |
-
"model": {
|
| 44 |
-
"inter_channels": 192,
|
| 45 |
-
"hidden_channels": 192,
|
| 46 |
-
"filter_channels": 768,
|
| 47 |
-
"n_heads": 2,
|
| 48 |
-
"n_layers": 6,
|
| 49 |
-
"kernel_size": 3,
|
| 50 |
-
"p_dropout": 0.1,
|
| 51 |
-
"resblock": "1",
|
| 52 |
-
"resblock_kernel_sizes": [
|
| 53 |
-
3,
|
| 54 |
-
7,
|
| 55 |
-
11
|
| 56 |
-
],
|
| 57 |
-
"resblock_dilation_sizes": [
|
| 58 |
-
[
|
| 59 |
-
1,
|
| 60 |
-
3,
|
| 61 |
-
5
|
| 62 |
-
],
|
| 63 |
-
[
|
| 64 |
-
1,
|
| 65 |
-
3,
|
| 66 |
-
5
|
| 67 |
-
],
|
| 68 |
-
[
|
| 69 |
-
1,
|
| 70 |
-
3,
|
| 71 |
-
5
|
| 72 |
-
]
|
| 73 |
-
],
|
| 74 |
-
"upsample_rates": [
|
| 75 |
-
8,
|
| 76 |
-
8,
|
| 77 |
-
2,
|
| 78 |
-
2,
|
| 79 |
-
2
|
| 80 |
-
],
|
| 81 |
-
"upsample_initial_channel": 512,
|
| 82 |
-
"upsample_kernel_sizes": [
|
| 83 |
-
16,
|
| 84 |
-
16,
|
| 85 |
-
4,
|
| 86 |
-
4,
|
| 87 |
-
4
|
| 88 |
-
],
|
| 89 |
-
"n_layers_q": 3,
|
| 90 |
-
"use_spectral_norm": false,
|
| 91 |
-
"gin_channels": 256,
|
| 92 |
-
"ssl_dim": 256,
|
| 93 |
-
"n_speakers": 200
|
| 94 |
-
},
|
| 95 |
-
"spk": {
|
| 96 |
-
"Diamond-Tiara": 0
|
| 97 |
-
}
|
| 98 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Diamond Tiara/kmeans.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7f8a63da11fb3bd33fca6a51ee9240535cf356d99515e1769ce36d27486f8d82
|
| 3 |
-
size 3083247
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Doctor Whooves/G_1668.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:210052b249f84c72e341f0c03970394ed5d9d807ccb53ec8b7c091e47c4c5f11
|
| 3 |
-
size 180896611
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Doctor Whooves/README.txt
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
Originally uploaded by ThunderAnon:
|
| 2 |
-
https://drive.google.com/drive/folders/1F0_Idv8G3s0R7RWxF_PctdxnAWUeyH_C?usp=sharing
|
| 3 |
-
Each zip and rar file in that link contained a large D_.pth file which is not needed for inference,
|
| 4 |
-
so I have reuploaded just the necessary files to the reduce the download time for Hay Say.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Doctor Whooves/config.json
DELETED
|
@@ -1,98 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"train": {
|
| 3 |
-
"log_interval": 200,
|
| 4 |
-
"eval_interval": 25000,
|
| 5 |
-
"seed": 1234,
|
| 6 |
-
"epochs": 1668,
|
| 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 |
-
},
|
| 43 |
-
"model": {
|
| 44 |
-
"inter_channels": 192,
|
| 45 |
-
"hidden_channels": 192,
|
| 46 |
-
"filter_channels": 768,
|
| 47 |
-
"n_heads": 2,
|
| 48 |
-
"n_layers": 6,
|
| 49 |
-
"kernel_size": 3,
|
| 50 |
-
"p_dropout": 0.1,
|
| 51 |
-
"resblock": "1",
|
| 52 |
-
"resblock_kernel_sizes": [
|
| 53 |
-
3,
|
| 54 |
-
7,
|
| 55 |
-
11
|
| 56 |
-
],
|
| 57 |
-
"resblock_dilation_sizes": [
|
| 58 |
-
[
|
| 59 |
-
1,
|
| 60 |
-
3,
|
| 61 |
-
5
|
| 62 |
-
],
|
| 63 |
-
[
|
| 64 |
-
1,
|
| 65 |
-
3,
|
| 66 |
-
5
|
| 67 |
-
],
|
| 68 |
-
[
|
| 69 |
-
1,
|
| 70 |
-
3,
|
| 71 |
-
5
|
| 72 |
-
]
|
| 73 |
-
],
|
| 74 |
-
"upsample_rates": [
|
| 75 |
-
8,
|
| 76 |
-
8,
|
| 77 |
-
2,
|
| 78 |
-
2,
|
| 79 |
-
2
|
| 80 |
-
],
|
| 81 |
-
"upsample_initial_channel": 512,
|
| 82 |
-
"upsample_kernel_sizes": [
|
| 83 |
-
16,
|
| 84 |
-
16,
|
| 85 |
-
4,
|
| 86 |
-
4,
|
| 87 |
-
4
|
| 88 |
-
],
|
| 89 |
-
"n_layers_q": 3,
|
| 90 |
-
"use_spectral_norm": false,
|
| 91 |
-
"gin_channels": 256,
|
| 92 |
-
"ssl_dim": 256,
|
| 93 |
-
"n_speakers": 200
|
| 94 |
-
},
|
| 95 |
-
"spk": {
|
| 96 |
-
"Doctor_Whooves": 0
|
| 97 |
-
}
|
| 98 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Flam/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Flam"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Flim/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Flim"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Fluttershy (singing, PS1)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Fluttershy (singing)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Gallus/G_10000.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ecd3b13e2eab233d1e659ecb8d5138f29bb42af40df6c1c99fcfef510acb9e72
|
| 3 |
-
size 542789469
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Gallus/README.txt
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
Originally uploaded by ThunderAnon:
|
| 2 |
-
https://drive.google.com/drive/folders/1F0_Idv8G3s0R7RWxF_PctdxnAWUeyH_C?usp=sharing
|
| 3 |
-
Each zip and rar file in that link contained a large D_.pth file which is not needed for inference,
|
| 4 |
-
so I have reuploaded just the necessary files to the reduce the download time for Hay Say.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Gallus/config.json
DELETED
|
@@ -1,98 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"train": {
|
| 3 |
-
"log_interval": 200,
|
| 4 |
-
"eval_interval": 25000,
|
| 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 |
-
},
|
| 43 |
-
"model": {
|
| 44 |
-
"inter_channels": 192,
|
| 45 |
-
"hidden_channels": 192,
|
| 46 |
-
"filter_channels": 768,
|
| 47 |
-
"n_heads": 2,
|
| 48 |
-
"n_layers": 6,
|
| 49 |
-
"kernel_size": 3,
|
| 50 |
-
"p_dropout": 0.1,
|
| 51 |
-
"resblock": "1",
|
| 52 |
-
"resblock_kernel_sizes": [
|
| 53 |
-
3,
|
| 54 |
-
7,
|
| 55 |
-
11
|
| 56 |
-
],
|
| 57 |
-
"resblock_dilation_sizes": [
|
| 58 |
-
[
|
| 59 |
-
1,
|
| 60 |
-
3,
|
| 61 |
-
5
|
| 62 |
-
],
|
| 63 |
-
[
|
| 64 |
-
1,
|
| 65 |
-
3,
|
| 66 |
-
5
|
| 67 |
-
],
|
| 68 |
-
[
|
| 69 |
-
1,
|
| 70 |
-
3,
|
| 71 |
-
5
|
| 72 |
-
]
|
| 73 |
-
],
|
| 74 |
-
"upsample_rates": [
|
| 75 |
-
8,
|
| 76 |
-
8,
|
| 77 |
-
2,
|
| 78 |
-
2,
|
| 79 |
-
2
|
| 80 |
-
],
|
| 81 |
-
"upsample_initial_channel": 512,
|
| 82 |
-
"upsample_kernel_sizes": [
|
| 83 |
-
16,
|
| 84 |
-
16,
|
| 85 |
-
4,
|
| 86 |
-
4,
|
| 87 |
-
4
|
| 88 |
-
],
|
| 89 |
-
"n_layers_q": 3,
|
| 90 |
-
"use_spectral_norm": false,
|
| 91 |
-
"gin_channels": 256,
|
| 92 |
-
"ssl_dim": 256,
|
| 93 |
-
"n_speakers": 200
|
| 94 |
-
},
|
| 95 |
-
"spk": {
|
| 96 |
-
"Gallus": 0
|
| 97 |
-
}
|
| 98 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Lightning Dust/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "ddm_LightningDust"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Luna (singing, PS1)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Luna (singing)"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Moon Dancer/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "ddm_Moondancer"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Ocellus/G_1668.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bce86b0dd26db1109bed9f4dcd9a0f40b0f9dc8e77fe8ac21f59f77fced352b3
|
| 3 |
-
size 548687709
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Ocellus/Readme.txt
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
Originally uploaded by ThunderAnon:
|
| 2 |
-
https://drive.google.com/drive/folders/1F0_Idv8G3s0R7RWxF_PctdxnAWUeyH_C?usp=sharing
|
| 3 |
-
Each zip and rar file in that link contained a large D_.pth file which is not needed for inference,
|
| 4 |
-
so I have reuploaded just the necessary files to the reduce the download time for Hay Say.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Ocellus/config.json
DELETED
|
@@ -1,104 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"train": {
|
| 3 |
-
"log_interval": 100,
|
| 4 |
-
"eval_interval": 1000,
|
| 5 |
-
"seed": 1234,
|
| 6 |
-
"epochs": 1668,
|
| 7 |
-
"learning_rate": 0.0001,
|
| 8 |
-
"betas": [
|
| 9 |
-
0.8,
|
| 10 |
-
0.99
|
| 11 |
-
],
|
| 12 |
-
"eps": 1e-09,
|
| 13 |
-
"batch_size": 7,
|
| 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 |
-
"Ocellus": 0
|
| 103 |
-
}
|
| 104 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Ocellus/kmeans.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:34a5c5b2bbdf005849dfc3d505a728b8be25a0e8bac5be5e04d54eb3c6f4ed6b
|
| 3 |
-
size 9242991
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (angry)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {angry}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (annoyed)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {annoyed}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (anxious)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {anxious}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (fearful)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {fear}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (happy)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {happy}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (neutral)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {neutral}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (nonverbal)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {nonverbal}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (sad shouting)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {sad shouting}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
so_vits_svc_4/Pinkie Pie (sad)/speaker.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"speaker": "Pinkie {sad}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|