Instructions to use azazen/train-dump with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use azazen/train-dump with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("azazen/train-dump", dtype="auto") - Notebooks
- Google Colab
- Kaggle
folder
Browse files- sovits/rim/so-vits-svc-fork-kaf/config.json +99 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/D_0.pth +3 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/D_6600.pth +3 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/G_0.pth +3 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/G_6600.pth +3 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/config.json +99 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/lightning_logs/version_0/events.out.tfevents.1682007183.83a1a0927a39.3198.0 +3 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/lightning_logs/version_0/events.out.tfevents.1682019239.4b9685bf812a.2589.0 +3 -0
- sovits/rim/so-vits-svc-fork-kaf/logs/44k/lightning_logs/version_0/hparams.yaml +84 -0
sovits/rim/so-vits-svc-fork-kaf/config.json
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train": {
|
| 3 |
+
"log_interval": 200,
|
| 4 |
+
"eval_interval": 200,
|
| 5 |
+
"seed": 1234,
|
| 6 |
+
"epochs": 10000,
|
| 7 |
+
"learning_rate": 5e-05,
|
| 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": 1,
|
| 26 |
+
"num_workers": 4,
|
| 27 |
+
"log_version": 0,
|
| 28 |
+
"ckpt_name_by_step": true,
|
| 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 |
+
"kaf_sing": 0,
|
| 97 |
+
"kaf_speech": 1
|
| 98 |
+
}
|
| 99 |
+
}
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/D_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:635be5c3409aaf3eec4135a1f5a771595683f3a6461ffc5bdea43441e50269a9
|
| 3 |
+
size 187018591
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/D_6600.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:432dc967e7cb998f7bf6969f4a0b68524eb9eb2c0dc63ca19b960acc8832e2a9
|
| 3 |
+
size 561098249
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/G_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a327c54e5731bed377bd38404bc32ab98e66a1b2777b0af4cc034d4d6914b0
|
| 3 |
+
size 180628517
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/G_6600.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bb138dd93860c41b230319304e6b8bda355371f870356509cd0956a0743101b
|
| 3 |
+
size 542789469
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/config.json
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train": {
|
| 3 |
+
"log_interval": 200,
|
| 4 |
+
"eval_interval": 200,
|
| 5 |
+
"seed": 1234,
|
| 6 |
+
"epochs": 10000,
|
| 7 |
+
"learning_rate": 5e-05,
|
| 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": 1,
|
| 26 |
+
"num_workers": 4,
|
| 27 |
+
"log_version": 0,
|
| 28 |
+
"ckpt_name_by_step": true,
|
| 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 |
+
"kaf_sing": 0,
|
| 97 |
+
"kaf_speech": 1
|
| 98 |
+
}
|
| 99 |
+
}
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/lightning_logs/version_0/events.out.tfevents.1682007183.83a1a0927a39.3198.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6513a47a235f5991af1a53ff534f2cb497f01a0162cca1317f1dcfc6ede401d0
|
| 3 |
+
size 16148463
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/lightning_logs/version_0/events.out.tfevents.1682019239.4b9685bf812a.2589.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99c82c6e5e36e424355c939df7691c6fca2cdae1ee96e397a0e1683a2d2a691f
|
| 3 |
+
size 70998574
|
sovits/rim/so-vits-svc-fork-kaf/logs/44k/lightning_logs/version_0/hparams.yaml
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: /kaggle/working/so-vits-svc-fork-kaf/logs/44k
|
| 54 |
+
reset_optimizer: false
|
| 55 |
+
spk: !!python/object:so_vits_svc_fork.hparams.HParams
|
| 56 |
+
kaf_sing: 0
|
| 57 |
+
kaf_speech: 1
|
| 58 |
+
train: !!python/object:so_vits_svc_fork.hparams.HParams
|
| 59 |
+
accumulate_grad_batches: 1
|
| 60 |
+
batch_size: 14
|
| 61 |
+
betas:
|
| 62 |
+
- 0.8
|
| 63 |
+
- 0.99
|
| 64 |
+
bf16_run: false
|
| 65 |
+
c_kl: 1.0
|
| 66 |
+
c_mel: 45
|
| 67 |
+
ckpt_name_by_step: true
|
| 68 |
+
epochs: 10000
|
| 69 |
+
eps: 1.0e-09
|
| 70 |
+
eval_interval: 400
|
| 71 |
+
fp16_run: false
|
| 72 |
+
init_lr_ratio: 1
|
| 73 |
+
keep_ckpts: 1
|
| 74 |
+
learning_rate: 5.0e-05
|
| 75 |
+
log_interval: 200
|
| 76 |
+
log_version: 0
|
| 77 |
+
lr_decay: 0.999875
|
| 78 |
+
max_speclen: 512
|
| 79 |
+
num_workers: 4
|
| 80 |
+
port: '8001'
|
| 81 |
+
seed: 1234
|
| 82 |
+
segment_size: 10240
|
| 83 |
+
use_sr: true
|
| 84 |
+
warmup_epochs: 0
|