Hugging Face's logo

subatomicseer
/
dddm_vc_checkpoints

Model card Files Community
dddm_vc_checkpoints
File size: 2,378 Bytes 
b754b20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
 
{
  "train": {
    "log_interval": 500,
    "eval_interval": 10000,
    "save_interval": 10000,
    "seed": 1234,
    "epochs": 1000,
    "optimizer": "adamw",
    "lr_decay_on": true,
    "learning_rate": 5e-5,
    "betas": [0.8, 0.99],
    "eps": 1e-9,
    "batch_size": 32,
    "fp16_run": false,
    "lr_decay": 0.999875,
    "segment_size": 35840,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 1,
    "c_diff": 1,
    "aug": true,
    "lambda_commit": 0.02
  },
  "data": {
    "train_filelist_path": "libritts/train_wav_final.txt",
    "test_filelist_path": "libritts/test_wav_final.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": 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": [5,4,4,2,2],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [11,8,8,4,4],
    "mixup_ratio": 0.6,
    "n_layers_q": 3,
    "use_spectral_norm": false,
    "encoder_hidden_size": 128
  },
    "f0_vq_params": {
      "l_bins": 20,
      "emb_width": 128,
      "mu": 0.99,
      "levels": 1
    },
   "f0_encoder_params": {
        "input_emb_width": 1,
        "output_emb_width": 128,
        "levels":  1,
        "downs_t": [4],
        "strides_t": [2],
        "width": 32,
        "depth": 4,
        "m_conv": 1.0,
        "dilation_growth_rate": 3
    },
    "f0_decoder_params": {
        "input_emb_width": 1,
        "output_emb_width": 128,
        "levels":  1,
        "downs_t": [4],
        "strides_t": [2],
        "width": 32,
        "depth": 4,
        "m_conv": 1.0,
        "dilation_growth_rate": 3
    },
    "diffusion" : {
      "dec_dim" : 128,
      "spk_dim" : 128,
      "use_ref_t" : false,
      "beta_min" : 0.05,
      "beta_max" : 20.0
    }
}