Hugging Face's logo

Spaces:
geoxten
/
suara_anime
Runtime error

App Files Community
1
geoxten commited on
Commit
1cd08a7
•
1 Parent(s): c5af650

Upload 2 files

Browse files
Files changed (2) hide show
  1. models/tannhauser/G_17600.pth +3 -0
  2. models/tannhauser/config.json +92 -92
models/tannhauser/G_17600.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0c00e8497ee213cdb2cb802236209bae5dabb489685d51ea02d93aa62f5c9f
3
+ size 542789469
models/tannhauser/config.json CHANGED
@@ -1,93 +1,93 @@
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": 32,
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": 99
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
- "n_speakers": 200
89
- },
90
- "spk": {
91
- "tannhauser": 0
92
- }
93
  }
 
1
+ {
2
+ "train": {
3
+ "log_interval": 100,
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": 1,
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": 3
25
+ },
26
+ "data": {
27
+ "training_files": "filelists/44k/train.txt",
28
+ "validation_files": "filelists/44k/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
+ "n_speakers": 200
89
+ },
90
+ "spk": {
91
+ "kobo": 0
92
+ }
93
  }