Hugging Face's logo

Spaces:
zzb1420
/
Bufeiyan-b-Bert-VITS2
Runtime error

App Files Community
Digital Xingtong commited on
Commit
c2c2209
•
1 Parent(s): 9fe9322

Upload 8 files

Browse files
Files changed (8) hide show
  1. logs/nailin/config.json +95 -0
  2. logs/nailin/nailin.pth +3 -0
  3. logs/nailv/config.json +95 -0
  4. logs/nailv/nailv_new.pth +3 -0
  5. logs/nailv_read/config.json +95 -0
  6. logs/nailv_read/nailv_read_new.pth +3 -0
  7. logs/xingtong/config.json +95 -0
  8. logs/xingtong/xt_new.pth +3 -0
logs/nailin/config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 10,
4
+ "eval_interval": 500,
5
+ "seed": 52,
6
+ "epochs": 2000,
7
+ "learning_rate": 0.00015,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 14,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 16384,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0
21
+ },
22
+ "data": {
23
+ "use_mel_posterior_encoder": false,
24
+ "training_files": "filelists/train.list",
25
+ "validation_files": "filelists/val.list",
26
+ "max_wav_value": 32768.0,
27
+ "sampling_rate": 44100,
28
+ "filter_length": 2048,
29
+ "hop_length": 512,
30
+ "win_length": 2048,
31
+ "n_mel_channels": 128,
32
+ "mel_fmin": 0.0,
33
+ "mel_fmax": null,
34
+ "add_blank": true,
35
+ "n_speakers": 1,
36
+ "cleaned_text": true,
37
+ "spk2id": {
38
+ "ign": 0
39
+ }
40
+ },
41
+ "model": {
42
+ "use_spk_conditioned_encoder": true,
43
+ "use_noise_scaled_mas": true,
44
+ "use_mel_posterior_encoder": false,
45
+ "use_duration_discriminator": true,
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
+ 8,
88
+ 2,
89
+ 2
90
+ ],
91
+ "n_layers_q": 3,
92
+ "use_spectral_norm": false,
93
+ "gin_channels": 256
94
+ }
95
+ }
logs/nailin/nailin.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b11d12d7cb1b27b7ab9082a0143d9b9df14582040fd95a825cdf627ce0b373d
3
+ size 629528157
logs/nailv/config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 10,
4
+ "eval_interval": 500,
5
+ "seed": 52,
6
+ "epochs": 2000,
7
+ "learning_rate": 0.00015,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 14,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 16384,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0
21
+ },
22
+ "data": {
23
+ "use_mel_posterior_encoder": false,
24
+ "training_files": "filelists/train.list",
25
+ "validation_files": "filelists/val.list",
26
+ "max_wav_value": 32768.0,
27
+ "sampling_rate": 44100,
28
+ "filter_length": 2048,
29
+ "hop_length": 512,
30
+ "win_length": 2048,
31
+ "n_mel_channels": 128,
32
+ "mel_fmin": 0.0,
33
+ "mel_fmax": null,
34
+ "add_blank": true,
35
+ "n_speakers": 1,
36
+ "cleaned_text": true,
37
+ "spk2id": {
38
+ "ign": 0
39
+ }
40
+ },
41
+ "model": {
42
+ "use_spk_conditioned_encoder": true,
43
+ "use_noise_scaled_mas": true,
44
+ "use_mel_posterior_encoder": false,
45
+ "use_duration_discriminator": true,
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
+ 8,
88
+ 2,
89
+ 2
90
+ ],
91
+ "n_layers_q": 3,
92
+ "use_spectral_norm": false,
93
+ "gin_channels": 256
94
+ }
95
+ }
logs/nailv/nailv_new.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9449f63274ae1b705bc3543d40f29f67d1a90df81cd03278856d7c48d53a640b
3
+ size 629528157
logs/nailv_read/config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 10,
4
+ "eval_interval": 500,
5
+ "seed": 52,
6
+ "epochs": 2000,
7
+ "learning_rate": 0.00015,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 14,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 16384,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0
21
+ },
22
+ "data": {
23
+ "use_mel_posterior_encoder": false,
24
+ "training_files": "filelists/train.list",
25
+ "validation_files": "filelists/val.list",
26
+ "max_wav_value": 32768.0,
27
+ "sampling_rate": 44100,
28
+ "filter_length": 2048,
29
+ "hop_length": 512,
30
+ "win_length": 2048,
31
+ "n_mel_channels": 128,
32
+ "mel_fmin": 0.0,
33
+ "mel_fmax": null,
34
+ "add_blank": true,
35
+ "n_speakers": 1,
36
+ "cleaned_text": true,
37
+ "spk2id": {
38
+ "ign": 0
39
+ }
40
+ },
41
+ "model": {
42
+ "use_spk_conditioned_encoder": true,
43
+ "use_noise_scaled_mas": true,
44
+ "use_mel_posterior_encoder": false,
45
+ "use_duration_discriminator": true,
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
+ 8,
88
+ 2,
89
+ 2
90
+ ],
91
+ "n_layers_q": 3,
92
+ "use_spectral_norm": false,
93
+ "gin_channels": 256
94
+ }
95
+ }
logs/nailv_read/nailv_read_new.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4044d2597de47c58f5f8ed8564b0b1b72ccb44809593522bf765f715a16c7891
3
+ size 629528157
logs/xingtong/config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 10,
4
+ "eval_interval": 500,
5
+ "seed": 52,
6
+ "epochs": 2000,
7
+ "learning_rate": 0.00015,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 14,
14
+ "fp16_run": false,
15
+ "lr_decay": 0.999875,
16
+ "segment_size": 16384,
17
+ "init_lr_ratio": 1,
18
+ "warmup_epochs": 0,
19
+ "c_mel": 45,
20
+ "c_kl": 1.0
21
+ },
22
+ "data": {
23
+ "use_mel_posterior_encoder": false,
24
+ "training_files": "filelists/train.list",
25
+ "validation_files": "filelists/val.list",
26
+ "max_wav_value": 32768.0,
27
+ "sampling_rate": 44100,
28
+ "filter_length": 2048,
29
+ "hop_length": 512,
30
+ "win_length": 2048,
31
+ "n_mel_channels": 128,
32
+ "mel_fmin": 0.0,
33
+ "mel_fmax": null,
34
+ "add_blank": true,
35
+ "n_speakers": 1,
36
+ "cleaned_text": true,
37
+ "spk2id": {
38
+ "ign": 0
39
+ }
40
+ },
41
+ "model": {
42
+ "use_spk_conditioned_encoder": true,
43
+ "use_noise_scaled_mas": true,
44
+ "use_mel_posterior_encoder": false,
45
+ "use_duration_discriminator": true,
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
+ 8,
88
+ 2,
89
+ 2
90
+ ],
91
+ "n_layers_q": 3,
92
+ "use_spectral_norm": false,
93
+ "gin_channels": 256
94
+ }
95
+ }
logs/xingtong/xt_new.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64034192d7af16b023bf263b76e624f458505ed9bfb1b8c3105ba41345c3da0
3
+ size 629528157