Hugging Face's logo

Wanlau
/
RVC_a-kiss-for-the-petals

Audio-to-Audio
RVC
Model card Files Community
Wanlau commited on
Commit
f29002f
•
1 Parent(s): 815846c

characters list

Browse files
Files changed (15) hide show
  1. Amane/config.json +46 -0
  2. Erisu/config.json +46 -0
  3. Kaede/config.json +46 -0
  4. Kaori/config.json +46 -0
  5. Koharu/config.json +46 -0
  6. Makoto/config.json +46 -0
  7. Nanami/config.json +46 -0
  8. Nanami_U/config.json +46 -0
  9. Rena/config.json +46 -0
  10. Reo_v2/config.json +46 -0
  11. Runa/config.json +46 -0
  12. Sara/config.json +46 -0
  13. Sizuku/config.json +46 -0
  14. Takako/config.json +46 -0
  15. Yuuna/config.json +46 -0
Amane/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Erisu/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Kaede/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Kaori/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Koharu/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Makoto/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Nanami/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Nanami_U/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Rena/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Reo_v2/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Runa/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Sara/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Sizuku/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Takako/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }
Yuuna/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train": {
3
+ "log_interval": 200,
4
+ "seed": 1234,
5
+ "epochs": 20000,
6
+ "learning_rate": 1e-4,
7
+ "betas": [0.8, 0.99],
8
+ "eps": 1e-9,
9
+ "batch_size": 4,
10
+ "fp16_run": true,
11
+ "lr_decay": 0.999875,
12
+ "segment_size": 12800,
13
+ "init_lr_ratio": 1,
14
+ "warmup_epochs": 0,
15
+ "c_mel": 45,
16
+ "c_kl": 1.0
17
+ },
18
+ "data": {
19
+ "max_wav_value": 32768.0,
20
+ "sampling_rate": 40000,
21
+ "filter_length": 2048,
22
+ "hop_length": 400,
23
+ "win_length": 2048,
24
+ "n_mel_channels": 125,
25
+ "mel_fmin": 0.0,
26
+ "mel_fmax": null
27
+ },
28
+ "model": {
29
+ "inter_channels": 192,
30
+ "hidden_channels": 192,
31
+ "filter_channels": 768,
32
+ "n_heads": 2,
33
+ "n_layers": 6,
34
+ "kernel_size": 3,
35
+ "p_dropout": 0,
36
+ "resblock": "1",
37
+ "resblock_kernel_sizes": [3,7,11],
38
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
39
+ "upsample_rates": [10,10,2,2],
40
+ "upsample_initial_channel": 512,
41
+ "upsample_kernel_sizes": [16,16,4,4],
42
+ "use_spectral_norm": false,
43
+ "gin_channels": 256,
44
+ "spk_embed_dim": 109
45
+ }
46
+ }