DiffSynth-Engine/diffsynth_engine/conf/models/ace/vae/vocoder.json at bff89eb8b8db5e850653275134f733561b6a84c0 · modelscope/DiffSynth-Engine · GitHub

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
{
    "depths": [
        3,
        3,
        9,
        3
    ],
    "dims": [
        128,
        256,
        384,
        512
    ],
    "f_max": 16000,
    "f_min": 40,
    "hop_length": 512,
    "input_channels": 128,
    "kernel_sizes": [
        7
    ],
    "n_fft": 2048,
    "n_mels": 128,
    "num_mels": 512,
    "post_conv_kernel_size": 13,
    "pre_conv_kernel_size": 13,
    "resblock_dilation_sizes": [
        [
            1,
            3,
            5
        ],
        [
            1,
            3,
            5
        ],
        [
            1,
            3,
            5
        ],
        [
            1,
            3,
            5
        ]
    ],
    "resblock_kernel_sizes": [
        3,
        7,
        11,
        13
    ],
    "sampling_rate": 44100,
    "upsample_initial_channel": 1024,
    "upsample_kernel_sizes": [
        8,
        8,
        4,
        4,
        4,
        4,
        4
    ],
    "upsample_rates": [
        4,
        4,
        2,
        2,
        2,
        2,
        2
    ],
    "use_template": false,
    "win_length": 2048
}