vit_model_kotae
Browse files- kotae2/D_0.pth +3 -0
- kotae2/D_178.pth +3 -0
- kotae2/D_200.pth +3 -0
- kotae2/D_223.pth +3 -0
- kotae2/G_0.pth +3 -0
- kotae2/G_178.pth +3 -0
- kotae2/G_200.pth +3 -0
- kotae2/G_223.pth +3 -0
- kotae2/config.json +98 -0
- kotae2/lightning_logs/version_0/events.out.tfevents.1683259964.75d0fd4bdacc.5533.0 +3 -0
- kotae2/lightning_logs/version_0/events.out.tfevents.1684307099.edde73ab1ed8.7435.0 +3 -0
- kotae2/lightning_logs/version_0/hparams.yaml +83 -0
kotae2/D_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:635be5c3409aaf3eec4135a1f5a771595683f3a6461ffc5bdea43441e50269a9
|
| 3 |
+
size 187018591
|
kotae2/D_178.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:007b725eb28453608a4b2955e079ce0fb36d9463f5f2f660d35df73057e2d902
|
| 3 |
+
size 561098249
|
kotae2/D_200.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:206cc8409f9c8ad6dc494f9b6419bdaf00bd6c243095f03f32e7a876d30b39ff
|
| 3 |
+
size 561098249
|
kotae2/D_223.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:349e066f0e7537b6be1d2d6b6f8cd5622115f12f365db0442622d2e394f7d86e
|
| 3 |
+
size 561098249
|
kotae2/G_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a327c54e5731bed377bd38404bc32ab98e66a1b2777b0af4cc034d4d6914b0
|
| 3 |
+
size 180628517
|
kotae2/G_178.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a69e4691177bff6bb0663b0cc500780679db04dc04e505013a2fff5d4770104c
|
| 3 |
+
size 542789469
|
kotae2/G_200.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0db7423e4b0f4a6935823b4a4690572241a6059bcc05b1a7d34dae1e7c1e9957
|
| 3 |
+
size 542789469
|
kotae2/G_223.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69214bc3c189007218f752592182b76def3d0e130c8485098c02a26e6fad886
|
| 3 |
+
size 542789469
|
kotae2/config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"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 |
+
"ayuki": 0
|
| 97 |
+
}
|
| 98 |
+
}
|
kotae2/lightning_logs/version_0/events.out.tfevents.1683259964.75d0fd4bdacc.5533.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58561fe9d22448f3e5c4d128f92fa20a9ff57414cf47d867572d8503929e8a21
|
| 3 |
+
size 28157549
|
kotae2/lightning_logs/version_0/events.out.tfevents.1684307099.edde73ab1ed8.7435.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:808575d422ded021fd1b013b32d95bd901a8f096af1579256735e3881c1ee112
|
| 3 |
+
size 19325092
|
kotae2/lightning_logs/version_0/hparams.yaml
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
data: !!python/object:so_vits_svc_fork.hparams.HParams
|
| 2 |
+
filter_length: 2048
|
| 3 |
+
hop_length: 512
|
| 4 |
+
max_wav_value: 32768.0
|
| 5 |
+
mel_fmax: 22050
|
| 6 |
+
mel_fmin: 0.0
|
| 7 |
+
n_mel_channels: 80
|
| 8 |
+
sampling_rate: 44100
|
| 9 |
+
training_files: filelists/44k/train.txt
|
| 10 |
+
validation_files: filelists/44k/val.txt
|
| 11 |
+
win_length: 2048
|
| 12 |
+
model: !!python/object:so_vits_svc_fork.hparams.HParams
|
| 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 |
+
n_layers_q: 3
|
| 21 |
+
n_speakers: 200
|
| 22 |
+
p_dropout: 0.1
|
| 23 |
+
resblock: '1'
|
| 24 |
+
resblock_dilation_sizes:
|
| 25 |
+
- - 1
|
| 26 |
+
- 3
|
| 27 |
+
- 5
|
| 28 |
+
- - 1
|
| 29 |
+
- 3
|
| 30 |
+
- 5
|
| 31 |
+
- - 1
|
| 32 |
+
- 3
|
| 33 |
+
- 5
|
| 34 |
+
resblock_kernel_sizes:
|
| 35 |
+
- 3
|
| 36 |
+
- 7
|
| 37 |
+
- 11
|
| 38 |
+
ssl_dim: 256
|
| 39 |
+
upsample_initial_channel: 512
|
| 40 |
+
upsample_kernel_sizes:
|
| 41 |
+
- 16
|
| 42 |
+
- 16
|
| 43 |
+
- 4
|
| 44 |
+
- 4
|
| 45 |
+
- 4
|
| 46 |
+
upsample_rates:
|
| 47 |
+
- 8
|
| 48 |
+
- 8
|
| 49 |
+
- 2
|
| 50 |
+
- 2
|
| 51 |
+
- 2
|
| 52 |
+
use_spectral_norm: false
|
| 53 |
+
model_dir: /content/output
|
| 54 |
+
reset_optimizer: false
|
| 55 |
+
spk: !!python/object:so_vits_svc_fork.hparams.HParams
|
| 56 |
+
Ayuki: 0
|
| 57 |
+
train: !!python/object:so_vits_svc_fork.hparams.HParams
|
| 58 |
+
accumulate_grad_batches: 1
|
| 59 |
+
batch_size: 16
|
| 60 |
+
betas:
|
| 61 |
+
- 0.8
|
| 62 |
+
- 0.99
|
| 63 |
+
bf16_run: false
|
| 64 |
+
c_kl: 1.0
|
| 65 |
+
c_mel: 45
|
| 66 |
+
ckpt_name_by_step: false
|
| 67 |
+
epochs: 10000
|
| 68 |
+
eps: 1.0e-09
|
| 69 |
+
eval_interval: 800
|
| 70 |
+
fp16_run: false
|
| 71 |
+
init_lr_ratio: 1
|
| 72 |
+
keep_ckpts: 3
|
| 73 |
+
learning_rate: 0.0001
|
| 74 |
+
log_interval: 200
|
| 75 |
+
log_version: 0
|
| 76 |
+
lr_decay: 0.999875
|
| 77 |
+
max_speclen: 512
|
| 78 |
+
num_workers: 4
|
| 79 |
+
port: '8001'
|
| 80 |
+
seed: 1234
|
| 81 |
+
segment_size: 10240
|
| 82 |
+
use_sr: true
|
| 83 |
+
warmup_epochs: 0
|