Upload 8 files
Browse files- configs/v1/32000.json +46 -0
- configs/v1/40000.json +46 -0
- configs/v1/44100.json +46 -0
- configs/v1/48000.json +46 -0
- configs/v2/32000.json +42 -0
- configs/v2/40000.json +42 -0
- configs/v2/44100.json +42 -0
- configs/v2/48000.json +42 -0
configs/v1/32000.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"epochs": 20000,
|
6 |
+
"learning_rate": 0.0001,
|
7 |
+
"betas": [0.8, 0.99],
|
8 |
+
"eps": 1e-09,
|
9 |
+
"batch_size": 4,
|
10 |
+
"lr_decay": 0.999875,
|
11 |
+
"segment_size": 12800,
|
12 |
+
"init_lr_ratio": 1,
|
13 |
+
"warmup_epochs": 0,
|
14 |
+
"c_mel": 45,
|
15 |
+
"c_kl": 1.0
|
16 |
+
},
|
17 |
+
"data": {
|
18 |
+
"max_wav_value": 32768.0,
|
19 |
+
"sample_rate": 32000,
|
20 |
+
"filter_length": 1024,
|
21 |
+
"hop_length": 320,
|
22 |
+
"win_length": 1024,
|
23 |
+
"n_mel_channels": 80,
|
24 |
+
"mel_fmin": 0.0,
|
25 |
+
"mel_fmax": null
|
26 |
+
},
|
27 |
+
"model": {
|
28 |
+
"inter_channels": 192,
|
29 |
+
"hidden_channels": 192,
|
30 |
+
"filter_channels": 768,
|
31 |
+
"text_enc_hidden_dim": 256,
|
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, 4, 2, 2, 2],
|
40 |
+
"upsample_initial_channel": 512,
|
41 |
+
"upsample_kernel_sizes": [16, 16, 4, 4, 4],
|
42 |
+
"use_spectral_norm": false,
|
43 |
+
"gin_channels": 256,
|
44 |
+
"spk_embed_dim": 109
|
45 |
+
}
|
46 |
+
}
|
configs/v1/40000.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"epochs": 20000,
|
6 |
+
"learning_rate": 0.0001,
|
7 |
+
"betas": [0.8, 0.99],
|
8 |
+
"eps": 1e-09,
|
9 |
+
"batch_size": 4,
|
10 |
+
"lr_decay": 0.999875,
|
11 |
+
"segment_size": 12800,
|
12 |
+
"init_lr_ratio": 1,
|
13 |
+
"warmup_epochs": 0,
|
14 |
+
"c_mel": 45,
|
15 |
+
"c_kl": 1.0
|
16 |
+
},
|
17 |
+
"data": {
|
18 |
+
"max_wav_value": 32768.0,
|
19 |
+
"sample_rate": 40000,
|
20 |
+
"filter_length": 2048,
|
21 |
+
"hop_length": 400,
|
22 |
+
"win_length": 2048,
|
23 |
+
"n_mel_channels": 125,
|
24 |
+
"mel_fmin": 0.0,
|
25 |
+
"mel_fmax": null
|
26 |
+
},
|
27 |
+
"model": {
|
28 |
+
"inter_channels": 192,
|
29 |
+
"hidden_channels": 192,
|
30 |
+
"filter_channels": 768,
|
31 |
+
"text_enc_hidden_dim": 256,
|
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 |
+
}
|
configs/v1/44100.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"epochs": 20000,
|
6 |
+
"learning_rate": 0.0001,
|
7 |
+
"betas": [0.8, 0.99],
|
8 |
+
"eps": 1e-09,
|
9 |
+
"batch_size": 4,
|
10 |
+
"lr_decay": 0.999875,
|
11 |
+
"segment_size": 15876,
|
12 |
+
"init_lr_ratio": 1,
|
13 |
+
"warmup_epochs": 0,
|
14 |
+
"c_mel": 45,
|
15 |
+
"c_kl": 1.0
|
16 |
+
},
|
17 |
+
"data": {
|
18 |
+
"max_wav_value": 32768.0,
|
19 |
+
"sample_rate": 44100,
|
20 |
+
"filter_length": 2048,
|
21 |
+
"hop_length": 441,
|
22 |
+
"win_length": 2048,
|
23 |
+
"n_mel_channels": 160,
|
24 |
+
"mel_fmin": 0.0,
|
25 |
+
"mel_fmax": null
|
26 |
+
},
|
27 |
+
"model": {
|
28 |
+
"inter_channels": 192,
|
29 |
+
"hidden_channels": 192,
|
30 |
+
"filter_channels": 768,
|
31 |
+
"text_enc_hidden_dim": 256,
|
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": [7, 7, 3, 3],
|
40 |
+
"upsample_initial_channel": 512,
|
41 |
+
"upsample_kernel_sizes": [14, 14, 6, 6],
|
42 |
+
"use_spectral_norm": false,
|
43 |
+
"gin_channels": 256,
|
44 |
+
"spk_embed_dim": 109
|
45 |
+
}
|
46 |
+
}
|
configs/v1/48000.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"epochs": 20000,
|
6 |
+
"learning_rate": 0.0001,
|
7 |
+
"betas": [0.8, 0.99],
|
8 |
+
"eps": 1e-09,
|
9 |
+
"batch_size": 4,
|
10 |
+
"lr_decay": 0.999875,
|
11 |
+
"segment_size": 11520,
|
12 |
+
"init_lr_ratio": 1,
|
13 |
+
"warmup_epochs": 0,
|
14 |
+
"c_mel": 45,
|
15 |
+
"c_kl": 1.0
|
16 |
+
},
|
17 |
+
"data": {
|
18 |
+
"max_wav_value": 32768.0,
|
19 |
+
"sample_rate": 48000,
|
20 |
+
"filter_length": 2048,
|
21 |
+
"hop_length": 480,
|
22 |
+
"win_length": 2048,
|
23 |
+
"n_mel_channels": 128,
|
24 |
+
"mel_fmin": 0.0,
|
25 |
+
"mel_fmax": null
|
26 |
+
},
|
27 |
+
"model": {
|
28 |
+
"inter_channels": 192,
|
29 |
+
"hidden_channels": 192,
|
30 |
+
"filter_channels": 768,
|
31 |
+
"text_enc_hidden_dim": 256,
|
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, 6, 2, 2, 2],
|
40 |
+
"upsample_initial_channel": 512,
|
41 |
+
"upsample_kernel_sizes": [16, 16, 4, 4, 4],
|
42 |
+
"use_spectral_norm": false,
|
43 |
+
"gin_channels": 256,
|
44 |
+
"spk_embed_dim": 109
|
45 |
+
}
|
46 |
+
}
|
configs/v2/32000.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"learning_rate": 0.0001,
|
6 |
+
"betas": [0.8, 0.99],
|
7 |
+
"eps": 1e-09,
|
8 |
+
"lr_decay": 0.999875,
|
9 |
+
"segment_size": 12800,
|
10 |
+
"c_mel": 45,
|
11 |
+
"c_kl": 1.0
|
12 |
+
},
|
13 |
+
"data": {
|
14 |
+
"max_wav_value": 32768.0,
|
15 |
+
"sample_rate": 32000,
|
16 |
+
"filter_length": 1024,
|
17 |
+
"hop_length": 320,
|
18 |
+
"win_length": 1024,
|
19 |
+
"n_mel_channels": 80,
|
20 |
+
"mel_fmin": 0.0,
|
21 |
+
"mel_fmax": null
|
22 |
+
},
|
23 |
+
"model": {
|
24 |
+
"inter_channels": 192,
|
25 |
+
"hidden_channels": 192,
|
26 |
+
"filter_channels": 768,
|
27 |
+
"text_enc_hidden_dim": 768,
|
28 |
+
"n_heads": 2,
|
29 |
+
"n_layers": 6,
|
30 |
+
"kernel_size": 3,
|
31 |
+
"p_dropout": 0,
|
32 |
+
"resblock": "1",
|
33 |
+
"resblock_kernel_sizes": [3, 7, 11],
|
34 |
+
"resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
|
35 |
+
"upsample_rates": [10, 8, 2, 2],
|
36 |
+
"upsample_initial_channel": 512,
|
37 |
+
"upsample_kernel_sizes": [20, 16, 4, 4],
|
38 |
+
"use_spectral_norm": false,
|
39 |
+
"gin_channels": 256,
|
40 |
+
"spk_embed_dim": 109
|
41 |
+
}
|
42 |
+
}
|
configs/v2/40000.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"learning_rate": 0.0001,
|
6 |
+
"betas": [0.8, 0.99],
|
7 |
+
"eps": 1e-09,
|
8 |
+
"lr_decay": 0.999875,
|
9 |
+
"segment_size": 12800,
|
10 |
+
"c_mel": 45,
|
11 |
+
"c_kl": 1.0
|
12 |
+
},
|
13 |
+
"data": {
|
14 |
+
"max_wav_value": 32768.0,
|
15 |
+
"sample_rate": 40000,
|
16 |
+
"filter_length": 2048,
|
17 |
+
"hop_length": 400,
|
18 |
+
"win_length": 2048,
|
19 |
+
"n_mel_channels": 125,
|
20 |
+
"mel_fmin": 0.0,
|
21 |
+
"mel_fmax": null
|
22 |
+
},
|
23 |
+
"model": {
|
24 |
+
"inter_channels": 192,
|
25 |
+
"hidden_channels": 192,
|
26 |
+
"filter_channels": 768,
|
27 |
+
"text_enc_hidden_dim": 768,
|
28 |
+
"n_heads": 2,
|
29 |
+
"n_layers": 6,
|
30 |
+
"kernel_size": 3,
|
31 |
+
"p_dropout": 0,
|
32 |
+
"resblock": "1",
|
33 |
+
"resblock_kernel_sizes": [3, 7, 11],
|
34 |
+
"resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
|
35 |
+
"upsample_rates": [10, 10, 2, 2],
|
36 |
+
"upsample_initial_channel": 512,
|
37 |
+
"upsample_kernel_sizes": [16, 16, 4, 4],
|
38 |
+
"use_spectral_norm": false,
|
39 |
+
"gin_channels": 256,
|
40 |
+
"spk_embed_dim": 109
|
41 |
+
}
|
42 |
+
}
|
configs/v2/44100.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"learning_rate": 0.0001,
|
6 |
+
"betas": [0.8, 0.99],
|
7 |
+
"eps": 1e-09,
|
8 |
+
"lr_decay": 0.999875,
|
9 |
+
"segment_size": 15876,
|
10 |
+
"c_mel": 45,
|
11 |
+
"c_kl": 1.0
|
12 |
+
},
|
13 |
+
"data": {
|
14 |
+
"max_wav_value": 32768.0,
|
15 |
+
"sample_rate": 44100,
|
16 |
+
"filter_length": 2048,
|
17 |
+
"hop_length": 441,
|
18 |
+
"win_length": 2048,
|
19 |
+
"n_mel_channels": 160,
|
20 |
+
"mel_fmin": 0.0,
|
21 |
+
"mel_fmax": null
|
22 |
+
},
|
23 |
+
"model": {
|
24 |
+
"inter_channels": 192,
|
25 |
+
"hidden_channels": 192,
|
26 |
+
"filter_channels": 768,
|
27 |
+
"text_enc_hidden_dim": 768,
|
28 |
+
"n_heads": 2,
|
29 |
+
"n_layers": 6,
|
30 |
+
"kernel_size": 3,
|
31 |
+
"p_dropout": 0,
|
32 |
+
"resblock": "1",
|
33 |
+
"resblock_kernel_sizes": [3, 7, 11],
|
34 |
+
"resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
|
35 |
+
"upsample_rates": [7, 7, 3, 3],
|
36 |
+
"upsample_initial_channel": 512,
|
37 |
+
"upsample_kernel_sizes": [14, 14, 6, 6],
|
38 |
+
"use_spectral_norm": false,
|
39 |
+
"gin_channels": 256,
|
40 |
+
"spk_embed_dim": 109
|
41 |
+
}
|
42 |
+
}
|
configs/v2/48000.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train": {
|
3 |
+
"log_interval": 200,
|
4 |
+
"seed": 1234,
|
5 |
+
"learning_rate": 0.0001,
|
6 |
+
"betas": [0.8, 0.99],
|
7 |
+
"eps": 1e-09,
|
8 |
+
"lr_decay": 0.999875,
|
9 |
+
"segment_size": 17280,
|
10 |
+
"c_mel": 45,
|
11 |
+
"c_kl": 1.0
|
12 |
+
},
|
13 |
+
"data": {
|
14 |
+
"max_wav_value": 32768.0,
|
15 |
+
"sample_rate": 48000,
|
16 |
+
"filter_length": 2048,
|
17 |
+
"hop_length": 480,
|
18 |
+
"win_length": 2048,
|
19 |
+
"n_mel_channels": 128,
|
20 |
+
"mel_fmin": 0.0,
|
21 |
+
"mel_fmax": null
|
22 |
+
},
|
23 |
+
"model": {
|
24 |
+
"inter_channels": 192,
|
25 |
+
"hidden_channels": 192,
|
26 |
+
"filter_channels": 768,
|
27 |
+
"text_enc_hidden_dim": 768,
|
28 |
+
"n_heads": 2,
|
29 |
+
"n_layers": 6,
|
30 |
+
"kernel_size": 3,
|
31 |
+
"p_dropout": 0,
|
32 |
+
"resblock": "1",
|
33 |
+
"resblock_kernel_sizes": [3, 7, 11],
|
34 |
+
"resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
|
35 |
+
"upsample_rates": [12, 10, 2, 2],
|
36 |
+
"upsample_initial_channel": 512,
|
37 |
+
"upsample_kernel_sizes": [24, 20, 4, 4],
|
38 |
+
"use_spectral_norm": false,
|
39 |
+
"gin_channels": 256,
|
40 |
+
"spk_embed_dim": 109
|
41 |
+
}
|
42 |
+
}
|