Hugging Face's logo

Spaces:
GroveStreet
/
GTA_SOVITS
Running

App Files Community
1
Katock commited on
Commit
b1f74f6
·
1 Parent(s): 6052830

add more model

Browse files
Files changed (13) hide show
  1. app.py +1 -1
  2. models/arthur/arthur.pth +3 -0
  3. models/arthur/config_arthur.json +94 -0
  4. models/arthur/cover.jpg +0 -0
  5. models/{carl/carl.pth → carl1/carl1.pth} +0 -0
  6. models/{carl/config_carl.json → carl1/config_carl1.json} +0 -0
  7. models/{carl → carl1}/cover.png +0 -0
  8. models/carl2/carl2.pth +3 -0
  9. models/carl2/config_carl2.json +94 -0
  10. models/carl2/cover.png +0 -0
  11. models/tomori/config_tomori.json +99 -0
  12. models/tomori/cover.png +0 -0
  13. models/tomori/tomori.pth +3 -0
app.py CHANGED
@@ -81,7 +81,7 @@ if __name__ == '__main__':
81
  for f in os.listdir("models"):
82
  name = f
83
  model = Svc(fr"models/{f}/{f}.pth", f"models/{f}/config_{f}.json", device=args.device)
84
- cover = f"models/{f}/cover.png" if os.path.exists(f"models/{f}/cover.png") else None
85
  models.append((name, cover, create_fn(model, name)))
86
  with gr.Blocks() as app:
87
  gr.Markdown(
 
81
  for f in os.listdir("models"):
82
  name = f
83
  model = Svc(fr"models/{f}/{f}.pth", f"models/{f}/config_{f}.json", device=args.device)
84
+ cover = f"models/{f}/cover.png" if os.path.exists(f"models/{f}/cover.png") else f"models/{f}/cover.jpg"
85
  models.append((name, cover, create_fn(model, name)))
86
  with gr.Blocks() as app:
87
  gr.Markdown(
models/arthur/arthur.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70fc73a4bf772cbdabb3703d45a466f54a45e446e869dd655038bbb41784e8ca
3
+ size 180653938
models/arthur/config_arthur.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": 0
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
+ "speech_encoder": "vec256l9",
89
+ "n_speakers": 1
90
+ },
91
+ "spk": {
92
+ "arthur": 0
93
+ }
94
+ }
models/arthur/cover.jpg ADDED
models/{carl/carl.pth → carl1/carl1.pth} RENAMED
File without changes
models/{carl/config_carl.json → carl1/config_carl1.json} RENAMED
File without changes
models/{carl → carl1}/cover.png RENAMED
File without changes
models/carl2/carl2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa229fa4e8de8f14b3b5cfd4b21552e7e8139656cb1ac617ff83d79aff2f241f
3
+ size 180665609
models/carl2/config_carl2.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": 4,
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": 20
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
+ "speech_encoder":"vec256l9",
89
+ "n_speakers": 1
90
+ },
91
+ "spk": {
92
+ "carl": 0
93
+ }
94
+ }
models/carl2/cover.png ADDED
models/tomori/config_tomori.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 800,
4
+ "eval_interval": 4000,
5
+ "seed": 1234,
6
+ "epochs": 30000,
7
+ "learning_rate": 0.0001,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 12,
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": 10,
25
+ "all_in_mem": true,
26
+ "vol_aug": true
27
+ },
28
+ "data": {
29
+ "training_files": "filelists/train.txt",
30
+ "validation_files": "filelists/val.txt",
31
+ "max_wav_value": 32768.0,
32
+ "sampling_rate": 44100,
33
+ "filter_length": 2048,
34
+ "hop_length": 512,
35
+ "win_length": 2048,
36
+ "n_mel_channels": 80,
37
+ "mel_fmin": 0.0,
38
+ "mel_fmax": 22050
39
+ },
40
+ "model": {
41
+ "inter_channels": 192,
42
+ "hidden_channels": 192,
43
+ "filter_channels": 768,
44
+ "n_heads": 2,
45
+ "n_layers": 6,
46
+ "kernel_size": 3,
47
+ "p_dropout": 0.1,
48
+ "resblock": "1",
49
+ "resblock_kernel_sizes": [
50
+ 3,
51
+ 7,
52
+ 11
53
+ ],
54
+ "resblock_dilation_sizes": [
55
+ [
56
+ 1,
57
+ 3,
58
+ 5
59
+ ],
60
+ [
61
+ 1,
62
+ 3,
63
+ 5
64
+ ],
65
+ [
66
+ 1,
67
+ 3,
68
+ 5
69
+ ]
70
+ ],
71
+ "upsample_rates": [
72
+ 8,
73
+ 8,
74
+ 2,
75
+ 2,
76
+ 2
77
+ ],
78
+ "upsample_initial_channel": 512,
79
+ "upsample_kernel_sizes": [
80
+ 16,
81
+ 16,
82
+ 4,
83
+ 4,
84
+ 4
85
+ ],
86
+ "n_layers_q": 3,
87
+ "use_spectral_norm": false,
88
+ "gin_channels": 768,
89
+ "ssl_dim": 768,
90
+ "n_speakers": 1,
91
+ "vocoder_name": "nsf-hifigan",
92
+ "speech_encoder": "vec768l12",
93
+ "speaker_embedding": false,
94
+ "vol_embedding": true
95
+ },
96
+ "spk": {
97
+ "tomori": 0
98
+ }
99
+ }
models/tomori/cover.png ADDED
models/tomori/tomori.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:121f2aeb8e3112e76d3cc1a8d53d75f4458f757d015692aaf2925c60a023c8f8
3
+ size 209238367