Hugging Face's logo

ImPavloh
/
Streamers-AI-Voices

Audio-to-Audio
music
Model card Files Community
ImPavloh commited on
Commit
eaf8141
•
1 Parent(s): 177e4c4

Voces iniciales de VoiceIt!

Browse files
Files changed (12) hide show
  1. DalasReview/G_8000.pth +3 -0
  2. DalasReview/config.json +93 -0
  3. Ibai/G_20000.pth +3 -0
  4. Ibai/config.json +94 -0
  5. Spreen/G_2400.pth +3 -0
  6. Spreen/config.json +93 -0
  7. TheGrefg/G_39200.pth +3 -0
  8. TheGrefg/config.json +94 -0
  9. WillyRex/G_32000.pth +3 -0
  10. WillyRex/config.json +94 -0
  11. XQc/G_25000.pth +3 -0
  12. XQc/config.json +98 -0
DalasReview/G_8000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb07b5b96e4634358305e1292b48bee1cf0e4c9143d3cdb18f65bbfba5542ae2
3
+ size 542781471
DalasReview/config.json ADDED
@@ -0,0 +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": 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": 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
+ "DalasReview": 0
92
+ }
93
+ }
Ibai/G_20000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b96cc5c41a6a3ae1777dd29515440a672f725933cff72f40dbb48ab42b4eed7
3
+ size 542178141
Ibai/config.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": 3,
25
+ "all_in_mem": false
26
+ },
27
+ "data": {
28
+ "training_files": "filelists/train.txt",
29
+ "validation_files": "filelists/val.txt",
30
+ "max_wav_value": 32768.0,
31
+ "sampling_rate": 44100,
32
+ "filter_length": 2048,
33
+ "hop_length": 512,
34
+ "win_length": 2048,
35
+ "n_mel_channels": 80,
36
+ "mel_fmin": 0.0,
37
+ "mel_fmax": 22050
38
+ },
39
+ "model": {
40
+ "inter_channels": 192,
41
+ "hidden_channels": 192,
42
+ "filter_channels": 768,
43
+ "n_heads": 2,
44
+ "n_layers": 6,
45
+ "kernel_size": 3,
46
+ "p_dropout": 0.1,
47
+ "resblock": "1",
48
+ "resblock_kernel_sizes": [
49
+ 3,
50
+ 7,
51
+ 11
52
+ ],
53
+ "resblock_dilation_sizes": [
54
+ [
55
+ 1,
56
+ 3,
57
+ 5
58
+ ],
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ]
69
+ ],
70
+ "upsample_rates": [
71
+ 8,
72
+ 8,
73
+ 2,
74
+ 2,
75
+ 2
76
+ ],
77
+ "upsample_initial_channel": 512,
78
+ "upsample_kernel_sizes": [
79
+ 16,
80
+ 16,
81
+ 4,
82
+ 4,
83
+ 4
84
+ ],
85
+ "n_layers_q": 3,
86
+ "use_spectral_norm": false,
87
+ "gin_channels": 256,
88
+ "ssl_dim": 256,
89
+ "n_speakers": 1
90
+ },
91
+ "spk": {
92
+ "Ibai": 0
93
+ }
94
+ }
Spreen/G_2400.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd54314d8425f185b2f757dd784ffb2e2d49ab30d77586019cf8faa091cc0793
3
+ size 542781471
Spreen/config.json ADDED
@@ -0,0 +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": 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": 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
+ "Spreen": 0
92
+ }
93
+ }
TheGrefg/G_39200.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d80814e295c15d80201fba0c4cd4d4fa0848bc5067bd379ff67fb3af0d0096
3
+ size 542178141
TheGrefg/config.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": 3,
25
+ "all_in_mem": false
26
+ },
27
+ "data": {
28
+ "training_files": "filelists/train.txt",
29
+ "validation_files": "filelists/val.txt",
30
+ "max_wav_value": 32768.0,
31
+ "sampling_rate": 44100,
32
+ "filter_length": 2048,
33
+ "hop_length": 512,
34
+ "win_length": 2048,
35
+ "n_mel_channels": 80,
36
+ "mel_fmin": 0.0,
37
+ "mel_fmax": 22050
38
+ },
39
+ "model": {
40
+ "inter_channels": 192,
41
+ "hidden_channels": 192,
42
+ "filter_channels": 768,
43
+ "n_heads": 2,
44
+ "n_layers": 6,
45
+ "kernel_size": 3,
46
+ "p_dropout": 0.1,
47
+ "resblock": "1",
48
+ "resblock_kernel_sizes": [
49
+ 3,
50
+ 7,
51
+ 11
52
+ ],
53
+ "resblock_dilation_sizes": [
54
+ [
55
+ 1,
56
+ 3,
57
+ 5
58
+ ],
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ]
69
+ ],
70
+ "upsample_rates": [
71
+ 8,
72
+ 8,
73
+ 2,
74
+ 2,
75
+ 2
76
+ ],
77
+ "upsample_initial_channel": 512,
78
+ "upsample_kernel_sizes": [
79
+ 16,
80
+ 16,
81
+ 4,
82
+ 4,
83
+ 4
84
+ ],
85
+ "n_layers_q": 3,
86
+ "use_spectral_norm": false,
87
+ "gin_channels": 256,
88
+ "ssl_dim": 256,
89
+ "n_speakers": 1
90
+ },
91
+ "spk": {
92
+ "TheGrefg": 0
93
+ }
94
+ }
WillyRex/G_32000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe02898462acb105418c414fba552047e37d39dc254408a833bc3eb35de7e9e1
3
+ size 542178141
WillyRex/config.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": 3,
25
+ "all_in_mem": false
26
+ },
27
+ "data": {
28
+ "training_files": "filelists/train.txt",
29
+ "validation_files": "filelists/val.txt",
30
+ "max_wav_value": 32768.0,
31
+ "sampling_rate": 44100,
32
+ "filter_length": 2048,
33
+ "hop_length": 512,
34
+ "win_length": 2048,
35
+ "n_mel_channels": 80,
36
+ "mel_fmin": 0.0,
37
+ "mel_fmax": 22050
38
+ },
39
+ "model": {
40
+ "inter_channels": 192,
41
+ "hidden_channels": 192,
42
+ "filter_channels": 768,
43
+ "n_heads": 2,
44
+ "n_layers": 6,
45
+ "kernel_size": 3,
46
+ "p_dropout": 0.1,
47
+ "resblock": "1",
48
+ "resblock_kernel_sizes": [
49
+ 3,
50
+ 7,
51
+ 11
52
+ ],
53
+ "resblock_dilation_sizes": [
54
+ [
55
+ 1,
56
+ 3,
57
+ 5
58
+ ],
59
+ [
60
+ 1,
61
+ 3,
62
+ 5
63
+ ],
64
+ [
65
+ 1,
66
+ 3,
67
+ 5
68
+ ]
69
+ ],
70
+ "upsample_rates": [
71
+ 8,
72
+ 8,
73
+ 2,
74
+ 2,
75
+ 2
76
+ ],
77
+ "upsample_initial_channel": 512,
78
+ "upsample_kernel_sizes": [
79
+ 16,
80
+ 16,
81
+ 4,
82
+ 4,
83
+ 4
84
+ ],
85
+ "n_layers_q": 3,
86
+ "use_spectral_norm": false,
87
+ "gin_channels": 256,
88
+ "ssl_dim": 256,
89
+ "n_speakers": 1
90
+ },
91
+ "spk": {
92
+ "WillyRex": 0
93
+ }
94
+ }
XQc/G_25000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f701572d94be10fe03dba9a92f2cbbaaba3ef8226086fe7f27959815d1ec522c
3
+ size 542789469
XQc/config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "eval_interval": 12500,
5
+ "seed": 1234,
6
+ "epochs": 1786,
7
+ "learning_rate": 0.0001,
8
+ "betas": [
9
+ 0.8,
10
+ 0.99
11
+ ],
12
+ "eps": 1e-09,
13
+ "batch_size": 7,
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": 4,
27
+ "log_version": 0,
28
+ "ckpt_name_by_step": false,
29
+ "accumulate_grad_batches": 1
30
+ },
31
+ "data": {
32
+ "training_files": "filelists/44k/train.txt",
33
+ "validation_files": "filelists/44k/val.txt",
34
+ "max_wav_value": 32768.0,
35
+ "sampling_rate": 44100,
36
+ "filter_length": 2048,
37
+ "hop_length": 512,
38
+ "win_length": 2048,
39
+ "n_mel_channels": 80,
40
+ "mel_fmin": 0.0,
41
+ "mel_fmax": 22050
42
+ },
43
+ "model": {
44
+ "inter_channels": 192,
45
+ "hidden_channels": 192,
46
+ "filter_channels": 768,
47
+ "n_heads": 2,
48
+ "n_layers": 6,
49
+ "kernel_size": 3,
50
+ "p_dropout": 0.1,
51
+ "resblock": "1",
52
+ "resblock_kernel_sizes": [
53
+ 3,
54
+ 7,
55
+ 11
56
+ ],
57
+ "resblock_dilation_sizes": [
58
+ [
59
+ 1,
60
+ 3,
61
+ 5
62
+ ],
63
+ [
64
+ 1,
65
+ 3,
66
+ 5
67
+ ],
68
+ [
69
+ 1,
70
+ 3,
71
+ 5
72
+ ]
73
+ ],
74
+ "upsample_rates": [
75
+ 8,
76
+ 8,
77
+ 2,
78
+ 2,
79
+ 2
80
+ ],
81
+ "upsample_initial_channel": 512,
82
+ "upsample_kernel_sizes": [
83
+ 16,
84
+ 16,
85
+ 4,
86
+ 4,
87
+ 4
88
+ ],
89
+ "n_layers_q": 3,
90
+ "use_spectral_norm": false,
91
+ "gin_channels": 256,
92
+ "ssl_dim": 256,
93
+ "n_speakers": 200
94
+ },
95
+ "spk": {
96
+ "XQc": 0
97
+ }
98
+ }