Spaces:
Sleeping
Sleeping
Rename trained/wdlm/trained_nahida_nahida.json to wdlm.json
Browse files- trained/wdlm/trained_nahida_nahida.json +0 -96
- wdlm.json +96 -0
trained/wdlm/trained_nahida_nahida.json
DELETED
@@ -1,96 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"train": {
|
3 |
-
"log_interval": 200,
|
4 |
-
"eval_interval": 800,
|
5 |
-
"seed": 1234,
|
6 |
-
"epochs": 10000,
|
7 |
-
"learning_rate": 0.00015,
|
8 |
-
"betas": [
|
9 |
-
0.8,
|
10 |
-
0.99
|
11 |
-
],
|
12 |
-
"eps": 1e-09,
|
13 |
-
"batch_size": 12,
|
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 |
-
"speech_encoder": "vec256l9",
|
91 |
-
"speaker_embedding": false
|
92 |
-
},
|
93 |
-
"spk": {
|
94 |
-
"nahida": 0
|
95 |
-
}
|
96 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wdlm.json
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 4,
|
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": 10,
|
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": 768,
|
88 |
+
"ssl_dim": 768,
|
89 |
+
"n_speakers": 1,
|
90 |
+
"speech_encoder": "vec768l12",
|
91 |
+
"speaker_embedding": false
|
92 |
+
},
|
93 |
+
"spk": {
|
94 |
+
"wdlm": 0
|
95 |
+
}
|
96 |
+
}
|