Hugging Face's logo

RMSnow
/
Vevo2

Safetensors
tts
vc
svs
svc
music
Model card Files
xet
Community
1
Vevo2
File size: 2,069 Bytes 
795b27d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "model_type": "Vocoder",
    "preprocess": {
        "hop_size": 480,
        "sample_rate": 24000,
        "max_length": 36000,
        "n_fft": 1920,
        "num_mels": 128,
        "win_size": 1920,
        "fmin": 0,
        "fmax": 12000,
        "mel_var": 8.14,
        "mel_mean": -4.92,
        "load_phone": false,
        "load_chromagram": false
    },
    "model": {
        "vocos": {
            "input_channels": 128,
            "dim": 1024,
            "intermediate_dim": 4096,
            "num_layers": 30,
            "n_fft": 1920,
            "hop_size": 480,
            "padding": "same"
        },
        "period_gan": {
            "max_downsample_channels": 1024,
            "channels": 64,
            "channel_increasing_factor": 2
        },
        "spec_gan": {
            "stft_params": {
                "fft_sizes": [
                    128,
                    256,
                    512,
                    1024,
                    2048
                ],
                "hop_sizes": [
                    32,
                    64,
                    128,
                    256,
                    512
                ],
                "win_lengths": [
                    128,
                    256,
                    512,
                    1024,
                    2048
                ],
                "window": "hann_window"
            },
            "in_channels": 1,
            "out_channels": 1,
            "channels": 64,
            "kernel_sizes": [
                5,
                3
            ],
            "max_downsample_channels": 1024,
            "down_scales": [
                2,
                2,
                2
            ],
            "use_weight_norm": true,
            "use_complex": false
        }
    },
    "loss": {
        "mel_loss": {
            "sample_rate": 24000
        },
        "disc_loss_weight": 1.0,
        "mel_loss_weight": 10.0,
        "adv_loss_weight": 2.0,
        "fm_loss_weight": 2.0,
        "spec_fm_loss_weight": 1.0
    },
}