Hugging Face's logo

CullenZhao
/
ASOUL-SVC

Text-to-Speech
Chinese
A-SOUL
asoul
jiaran
VirtualIdol
Vtuber
Model card Files
xet
 Community
CullenZhao commited on
Commit
8f675a6
·
verified ·
1 Parent(s): fe59c3f

Upload 5 files

Browse files

Add SVC models of Jiaran Diana, Beila Bella, Nailin Eileen, Sinuo Gladys, Xinyi Fiona of A-SOUL / Zhijiang.

Files changed (5) hide show
  1. G_65600.pth +3 -0
  2. config_beilanailin.json +106 -0
  3. config_jiaran.json +105 -0
  4. config_sinuo.json +105 -0
  5. config_xinyi.json +105 -0
G_65600.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56344e7ecb17f598b904fe2eeff2fe39a0951611607274257db1a3d48243dad1
3
+ size 627914525
config_beilanailin.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 16,
14
+ "fp16_run": false,
15
+ "half_type": "fp16",
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
+ "all_in_mem": true,
27
+ "vol_aug": false
28
+ },
29
+ "data": {
30
+ "training_files": "filelists/train.txt",
31
+ "validation_files": "filelists/val.txt",
32
+ "max_wav_value": 32768.0,
33
+ "sampling_rate": 44100,
34
+ "filter_length": 2048,
35
+ "hop_length": 512,
36
+ "win_length": 2048,
37
+ "n_mel_channels": 80,
38
+ "mel_fmin": 0.0,
39
+ "mel_fmax": 22050,
40
+ "unit_interpolate_mode": "nearest"
41
+ },
42
+ "model": {
43
+ "inter_channels": 192,
44
+ "hidden_channels": 192,
45
+ "filter_channels": 768,
46
+ "n_heads": 2,
47
+ "n_layers": 6,
48
+ "kernel_size": 3,
49
+ "p_dropout": 0.1,
50
+ "resblock": "1",
51
+ "resblock_kernel_sizes": [
52
+ 3,
53
+ 7,
54
+ 11
55
+ ],
56
+ "resblock_dilation_sizes": [
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ],
67
+ [
68
+ 1,
69
+ 3,
70
+ 5
71
+ ]
72
+ ],
73
+ "upsample_rates": [
74
+ 8,
75
+ 8,
76
+ 2,
77
+ 2,
78
+ 2
79
+ ],
80
+ "upsample_initial_channel": 512,
81
+ "upsample_kernel_sizes": [
82
+ 16,
83
+ 16,
84
+ 4,
85
+ 4,
86
+ 4
87
+ ],
88
+ "n_layers_q": 3,
89
+ "n_flow_layer": 4,
90
+ "use_spectral_norm": false,
91
+ "gin_channels": 768,
92
+ "ssl_dim": 768,
93
+ "n_speakers": 2,
94
+ "vocoder_name": "nsf-hifigan",
95
+ "speech_encoder": "vec768l12",
96
+ "speaker_embedding": false,
97
+ "vol_embedding": false,
98
+ "use_depthwise_conv": false,
99
+ "flow_share_parameter": false,
100
+ "use_automatic_f0_prediction": true
101
+ },
102
+ "spk": {
103
+ "beila": 0,
104
+ "nailin": 1
105
+ }
106
+ }
config_jiaran.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 16,
14
+ "fp16_run": false,
15
+ "half_type": "fp16",
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
+ "all_in_mem": true,
27
+ "vol_aug": false
28
+ },
29
+ "data": {
30
+ "training_files": "filelists/train.txt",
31
+ "validation_files": "filelists/val.txt",
32
+ "max_wav_value": 32768.0,
33
+ "sampling_rate": 44100,
34
+ "filter_length": 2048,
35
+ "hop_length": 512,
36
+ "win_length": 2048,
37
+ "n_mel_channels": 80,
38
+ "mel_fmin": 0.0,
39
+ "mel_fmax": 22050,
40
+ "unit_interpolate_mode": "nearest"
41
+ },
42
+ "model": {
43
+ "inter_channels": 192,
44
+ "hidden_channels": 192,
45
+ "filter_channels": 768,
46
+ "n_heads": 2,
47
+ "n_layers": 6,
48
+ "kernel_size": 3,
49
+ "p_dropout": 0.1,
50
+ "resblock": "1",
51
+ "resblock_kernel_sizes": [
52
+ 3,
53
+ 7,
54
+ 11
55
+ ],
56
+ "resblock_dilation_sizes": [
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ],
67
+ [
68
+ 1,
69
+ 3,
70
+ 5
71
+ ]
72
+ ],
73
+ "upsample_rates": [
74
+ 8,
75
+ 8,
76
+ 2,
77
+ 2,
78
+ 2
79
+ ],
80
+ "upsample_initial_channel": 512,
81
+ "upsample_kernel_sizes": [
82
+ 16,
83
+ 16,
84
+ 4,
85
+ 4,
86
+ 4
87
+ ],
88
+ "n_layers_q": 3,
89
+ "n_flow_layer": 4,
90
+ "use_spectral_norm": false,
91
+ "gin_channels": 768,
92
+ "ssl_dim": 768,
93
+ "n_speakers": 1,
94
+ "vocoder_name": "nsf-hifigan",
95
+ "speech_encoder": "vec768l12",
96
+ "speaker_embedding": false,
97
+ "vol_embedding": false,
98
+ "use_depthwise_conv": false,
99
+ "flow_share_parameter": false,
100
+ "use_automatic_f0_prediction": true
101
+ },
102
+ "spk": {
103
+ "jiaran": 0
104
+ }
105
+ }
config_sinuo.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "eval_interval": 1200,
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": 16,
14
+ "fp16_run": false,
15
+ "half_type": "fp16",
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": "10001",
25
+ "keep_ckpts": 3,
26
+ "all_in_mem": true,
27
+ "vol_aug": false
28
+ },
29
+ "data": {
30
+ "training_files": "filelists/train.txt",
31
+ "validation_files": "filelists/val.txt",
32
+ "max_wav_value": 32768.0,
33
+ "sampling_rate": 44100,
34
+ "filter_length": 2048,
35
+ "hop_length": 512,
36
+ "win_length": 2048,
37
+ "n_mel_channels": 80,
38
+ "mel_fmin": 0.0,
39
+ "mel_fmax": 22050,
40
+ "unit_interpolate_mode": "nearest"
41
+ },
42
+ "model": {
43
+ "inter_channels": 192,
44
+ "hidden_channels": 192,
45
+ "filter_channels": 768,
46
+ "n_heads": 2,
47
+ "n_layers": 6,
48
+ "kernel_size": 3,
49
+ "p_dropout": 0.1,
50
+ "resblock": "1",
51
+ "resblock_kernel_sizes": [
52
+ 3,
53
+ 7,
54
+ 11
55
+ ],
56
+ "resblock_dilation_sizes": [
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ],
67
+ [
68
+ 1,
69
+ 3,
70
+ 5
71
+ ]
72
+ ],
73
+ "upsample_rates": [
74
+ 8,
75
+ 8,
76
+ 2,
77
+ 2,
78
+ 2
79
+ ],
80
+ "upsample_initial_channel": 512,
81
+ "upsample_kernel_sizes": [
82
+ 16,
83
+ 16,
84
+ 4,
85
+ 4,
86
+ 4
87
+ ],
88
+ "n_layers_q": 3,
89
+ "n_flow_layer": 4,
90
+ "use_spectral_norm": false,
91
+ "gin_channels": 768,
92
+ "ssl_dim": 768,
93
+ "n_speakers": 1,
94
+ "vocoder_name": "nsf-hifigan",
95
+ "speech_encoder": "vec768l12",
96
+ "speaker_embedding": false,
97
+ "vol_embedding": false,
98
+ "use_depthwise_conv": false,
99
+ "flow_share_parameter": false,
100
+ "use_automatic_f0_prediction": true
101
+ },
102
+ "spk": {
103
+ "sinuo": 0
104
+ }
105
+ }
config_xinyi.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "eval_interval": 1200,
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": 16,
14
+ "fp16_run": false,
15
+ "half_type": "fp16",
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": "10001",
25
+ "keep_ckpts": 3,
26
+ "all_in_mem": true,
27
+ "vol_aug": false
28
+ },
29
+ "data": {
30
+ "training_files": "filelists/train.txt",
31
+ "validation_files": "filelists/val.txt",
32
+ "max_wav_value": 32768.0,
33
+ "sampling_rate": 44100,
34
+ "filter_length": 2048,
35
+ "hop_length": 512,
36
+ "win_length": 2048,
37
+ "n_mel_channels": 80,
38
+ "mel_fmin": 0.0,
39
+ "mel_fmax": 22050,
40
+ "unit_interpolate_mode": "nearest"
41
+ },
42
+ "model": {
43
+ "inter_channels": 192,
44
+ "hidden_channels": 192,
45
+ "filter_channels": 768,
46
+ "n_heads": 2,
47
+ "n_layers": 6,
48
+ "kernel_size": 3,
49
+ "p_dropout": 0.1,
50
+ "resblock": "1",
51
+ "resblock_kernel_sizes": [
52
+ 3,
53
+ 7,
54
+ 11
55
+ ],
56
+ "resblock_dilation_sizes": [
57
+ [
58
+ 1,
59
+ 3,
60
+ 5
61
+ ],
62
+ [
63
+ 1,
64
+ 3,
65
+ 5
66
+ ],
67
+ [
68
+ 1,
69
+ 3,
70
+ 5
71
+ ]
72
+ ],
73
+ "upsample_rates": [
74
+ 8,
75
+ 8,
76
+ 2,
77
+ 2,
78
+ 2
79
+ ],
80
+ "upsample_initial_channel": 512,
81
+ "upsample_kernel_sizes": [
82
+ 16,
83
+ 16,
84
+ 4,
85
+ 4,
86
+ 4
87
+ ],
88
+ "n_layers_q": 3,
89
+ "n_flow_layer": 4,
90
+ "use_spectral_norm": false,
91
+ "gin_channels": 768,
92
+ "ssl_dim": 768,
93
+ "n_speakers": 1,
94
+ "vocoder_name": "nsf-hifigan",
95
+ "speech_encoder": "vec768l12",
96
+ "speaker_embedding": false,
97
+ "vol_embedding": false,
98
+ "use_depthwise_conv": false,
99
+ "flow_share_parameter": false,
100
+ "use_automatic_f0_prediction": true
101
+ },
102
+ "spk": {
103
+ "xinyi": 0
104
+ }
105
+ }