Hugging Face's logo

kevinwang676
/
talktalkai-qing

Transformers
TensorBoard
Inference Endpoints
Model card Files Metrics Community
2
kevinwang676 commited on
Commit
a7365f0
•
1 Parent(s): 73b209f

Upload 6 files

Browse files
Files changed (6) hide show
  1. D_10000.pth +3 -0
  2. G_10000.pth +3 -0
  3. config.json +105 -0
  4. kmeans.pt +3 -0
  5. lightning_logs/version_0/events.out.tfevents.1688563570.e1f0bd0f00d0.2500.0 +3 -0
  6. lightning_logs/version_0/hparams.yaml +89 -0
D_10000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f7e8d65f59211e89a0ec0a8504fcb73aba4402d29b81d26017922a1ba12f08
3
+ size 561098249
G_10000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c7c18f04865b520c88a7f71def0806b2e022d388f722e8064ae802f8bf490c8
3
+ size 548687709
config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
4
+ "eval_interval": 500,
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": 32,
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": 32,
27
+ "log_version": 0,
28
+ "ckpt_name_by_step": false,
29
+ "accumulate_grad_batches": 1,
30
+ "persistent_workers": true
31
+ },
32
+ "data": {
33
+ "training_files": "filelists/44k/train.txt",
34
+ "validation_files": "filelists/44k/val.txt",
35
+ "max_wav_value": 32768.0,
36
+ "sampling_rate": 44100,
37
+ "filter_length": 2048,
38
+ "hop_length": 512,
39
+ "win_length": 2048,
40
+ "n_mel_channels": 80,
41
+ "mel_fmin": 0.0,
42
+ "mel_fmax": 22050,
43
+ "contentvec_final_proj": false
44
+ },
45
+ "model": {
46
+ "inter_channels": 192,
47
+ "hidden_channels": 192,
48
+ "filter_channels": 768,
49
+ "n_heads": 2,
50
+ "n_layers": 6,
51
+ "kernel_size": 3,
52
+ "p_dropout": 0.1,
53
+ "resblock": "1",
54
+ "resblock_kernel_sizes": [
55
+ 3,
56
+ 7,
57
+ 11
58
+ ],
59
+ "resblock_dilation_sizes": [
60
+ [
61
+ 1,
62
+ 3,
63
+ 5
64
+ ],
65
+ [
66
+ 1,
67
+ 3,
68
+ 5
69
+ ],
70
+ [
71
+ 1,
72
+ 3,
73
+ 5
74
+ ]
75
+ ],
76
+ "upsample_rates": [
77
+ 8,
78
+ 8,
79
+ 2,
80
+ 2,
81
+ 2
82
+ ],
83
+ "upsample_initial_channel": 512,
84
+ "upsample_kernel_sizes": [
85
+ 16,
86
+ 16,
87
+ 4,
88
+ 4,
89
+ 4
90
+ ],
91
+ "n_layers_q": 3,
92
+ "use_spectral_norm": false,
93
+ "gin_channels": 256,
94
+ "ssl_dim": 768,
95
+ "n_speakers": 200,
96
+ "type_": "hifi-gan",
97
+ "pretrained": {
98
+ "D_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth",
99
+ "G_0.pth": "https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth"
100
+ }
101
+ },
102
+ "spk": {
103
+ "qing": 0
104
+ }
105
+ }
kmeans.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b968cd1ba732fb8d15eb659990130fc872734bbb869d7bdbb96fd308e37b47d
3
+ size 9243311
lightning_logs/version_0/events.out.tfevents.1688563570.e1f0bd0f00d0.2500.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b6929ceefcc81a2293ccdca186a35831dd0411c1166493eceea306f39296ed
3
+ size 538734395
lightning_logs/version_0/hparams.yaml ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ data: !!python/object:so_vits_svc_fork.hparams.HParams
2
+ contentvec_final_proj: false
3
+ filter_length: 2048
4
+ hop_length: 512
5
+ max_wav_value: 32768.0
6
+ mel_fmax: 22050
7
+ mel_fmin: 0.0
8
+ n_mel_channels: 80
9
+ sampling_rate: 44100
10
+ training_files: filelists/44k/train.txt
11
+ validation_files: filelists/44k/val.txt
12
+ win_length: 2048
13
+ model: !!python/object:so_vits_svc_fork.hparams.HParams
14
+ filter_channels: 768
15
+ gin_channels: 256
16
+ hidden_channels: 192
17
+ inter_channels: 192
18
+ kernel_size: 3
19
+ n_heads: 2
20
+ n_layers: 6
21
+ n_layers_q: 3
22
+ n_speakers: 200
23
+ p_dropout: 0.1
24
+ pretrained: !!python/object:so_vits_svc_fork.hparams.HParams
25
+ D_0.pth: https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_D_320000.pth
26
+ G_0.pth: https://huggingface.co/datasets/ms903/sovits4.0-768vec-layer12/resolve/main/sovits_768l12_pre_large_320k/clean_G_320000.pth
27
+ resblock: '1'
28
+ resblock_dilation_sizes:
29
+ - - 1
30
+ - 3
31
+ - 5
32
+ - - 1
33
+ - 3
34
+ - 5
35
+ - - 1
36
+ - 3
37
+ - 5
38
+ resblock_kernel_sizes:
39
+ - 3
40
+ - 7
41
+ - 11
42
+ ssl_dim: 768
43
+ type_: hifi-gan
44
+ upsample_initial_channel: 512
45
+ upsample_kernel_sizes:
46
+ - 16
47
+ - 16
48
+ - 4
49
+ - 4
50
+ - 4
51
+ upsample_rates:
52
+ - 8
53
+ - 8
54
+ - 2
55
+ - 2
56
+ - 2
57
+ use_spectral_norm: false
58
+ model_dir: logs/44k
59
+ reset_optimizer: false
60
+ spk: !!python/object:so_vits_svc_fork.hparams.HParams
61
+ qing: 0
62
+ train: !!python/object:so_vits_svc_fork.hparams.HParams
63
+ accumulate_grad_batches: 1
64
+ batch_size: 32
65
+ betas:
66
+ - 0.8
67
+ - 0.99
68
+ bf16_run: false
69
+ c_kl: 1.0
70
+ c_mel: 45
71
+ ckpt_name_by_step: false
72
+ epochs: 10000
73
+ eps: 1.0e-09
74
+ eval_interval: 500
75
+ fp16_run: false
76
+ init_lr_ratio: 1
77
+ keep_ckpts: 3
78
+ learning_rate: 0.0001
79
+ log_interval: 100
80
+ log_version: 0
81
+ lr_decay: 0.999875
82
+ max_speclen: 512
83
+ num_workers: 32
84
+ persistent_workers: true
85
+ port: '8001'
86
+ seed: 1234
87
+ segment_size: 10240
88
+ use_sr: true
89
+ warmup_epochs: 0