Hugging Face's logo

audo
/
HierSpeechpp

Model card Files Community
5
HierSpeechpp
File size: 1,378 Bytes 
9dbe3d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "train": {
      "log_interval": 200,
      "eval_interval": 10000,
      "save_interval": 10000,
      "seed": 1234,
      "epochs": 20000,
      "learning_rate": 2e-4,
      "betas": [0.8, 0.99],
      "eps": 1e-9,
      "batch_size": 32,
      "fp16_run": false,
      "lr_decay": 0.999,
      "segment_size": 192000,
      "init_lr_ratio": 1,
      "warmup_epochs": 0,
      "c_mel": 10,
      "c_kl": 0.1,
      "c_pho": 45.0,
      "c_f0": 1,
      "aug": true
    },
    "data": {
      "train_filelist_path": "filelists/train_wav.txt",
      "test_filelist_path": "filelists/test_wav.txt",
      "text_cleaners":["english_cleaners2"],
      "max_wav_value": 32768.0,
      "sampling_rate": 16000,
      "filter_length": 1280,
      "hop_length": 320,
      "win_length": 1280,
      "n_mel_channels": 80,
      "mel_fmin": 0,
      "mel_fmax": 8000,
      "add_blank": true,
      "n_speakers": 0,
      "cleaned_text": true,
      "aug_rate": 1.0,
      "top_db": 20
    },
    "model": {
        "inter_channels": 256,
        "hidden_channels": 256,
        "filter_channels": 1024,
        "n_heads": 4,
        "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]],
        "use_spectral_norm": false
      }
  }