File size: 1,513 Bytes
fa4c2d7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
{
     "train": {
       "log_interval": 200,
       "eval_interval": 50000,
       "seed": 1234,
       "epochs": 10000,
       "learning_rate": 2e-4,
       "betas": [0.8, 0.99],
       "eps": 1e-9,
       "batch_size": 8,
       "fp16_run": true,
       "lr_decay": 0.999875,
       "segment_size": 8192,
       "init_lr_ratio": 1,
       "warmup_epochs": 0,
       "c_mel": 45,
       "c_kl": 1.0
     },
     "data": {
       "wavs_dir": "../DATA/wavs",
       "speaker_embedding_dir": "../DATA/embedding",
       "training_files":"../DATA/train.txt",
       "validation_files":"../DATA/val.txt",
       "text_cleaners":["english_cleaners2"],
       "max_wav_value": 32768.0,
       "sampling_rate": 22050,
       "filter_length": 1024,
       "hop_length": 256,
       "win_length": 1024,
       "n_mel_channels": 80,
       "mel_fmin": 0.0,
       "mel_fmax": null,
       "add_blank": true,
       "n_speakers": 109,
       "cleaned_text": true
     },
     "model": {
       "inter_channels": 192,
       "hidden_channels": 192,
       "filter_channels": 768,
       "n_heads": 2,
       "n_layers": 6,
       "kernel_size": 3,
       "p_dropout": 0.1,
       "resblock": "1",
       "resblock_kernel_sizes": [3,7,11],
       "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
       "upsample_rates": [8,8,2,2],
       "upsample_initial_channel": 512,
       "upsample_kernel_sizes": [16,16,4,4],
       "n_layers_q": 3,
       "use_spectral_norm": false,
       "gin_channels": 256
     }
   }