File size: 5,757 Bytes
0bb29f1
 
 
 
 
 
 
3b0b39f
0bb29f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import Conv1d, ConvTranspose1d
from torch.nn.utils import remove_weight_norm, weight_norm
from transformers import PreTrainedModel

from .configuration_hifigan import HiFiGANConfig

LRELU_SLOPE = 0.1


def init_weights(m, mean=0.0, std=0.01):
    classname = m.__class__.__name__
    if classname.find("Conv") != -1:
        m.weight.data.normal_(mean, std)


def get_padding(kernel_size, dilation=1):
    return (kernel_size * dilation - dilation) // 2


class ResBlock(torch.nn.Module):
    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
        super(ResBlock, self).__init__()
        self.convs1 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=get_padding(kernel_size, dilation[1]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[2],
                        padding=get_padding(kernel_size, dilation[2]),
                    )
                ),
            ]
        )
        self.convs1.apply(init_weights)

        self.convs2 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
            ]
        )
        self.convs2.apply(init_weights)

    def forward(self, x):
        for c1, c2 in zip(self.convs1, self.convs2):
            xt = F.leaky_relu(x, LRELU_SLOPE)
            xt = c1(xt)
            xt = F.leaky_relu(xt, LRELU_SLOPE)
            xt = c2(xt)
            x = xt + x
        return x

    def remove_weight_norm(self):
        for layer in self.convs1:
            remove_weight_norm(layer)
        for layer in self.convs2:
            remove_weight_norm(layer)


class HiFiGAN(PreTrainedModel):
    config_class = HiFiGANConfig

    def __init__(self, config):
        super().__init__(config)
        self.num_kernels = len(config.resblock_kernel_sizes)
        self.num_upsamples = len(config.upsample_rates)
        self.conv_pre = weight_norm(
            Conv1d(
                config.model_in_dim,
                config.upsample_initial_channel,
                7,
                1,
                padding=3,
            )
        )

        self.ups = nn.ModuleList()
        for i, (u, k) in enumerate(
            zip(config.upsample_rates, config.upsample_kernel_sizes)
        ):
            self.ups.append(
                weight_norm(
                    ConvTranspose1d(
                        config.upsample_initial_channel // (2**i),
                        config.upsample_initial_channel // (2 ** (i + 1)),
                        k,
                        u,
                        padding=(k - u) // 2,
                    )
                )
            )

        self.resblocks = nn.ModuleList()
        for i in range(len(self.ups)):
            ch = config.upsample_initial_channel // (2 ** (i + 1))
            for k, d in zip(
                config.resblock_kernel_sizes, config.resblock_dilation_sizes
            ):
                self.resblocks.append(ResBlock(ch, k, d))

        self.conv_post = weight_norm(Conv1d(ch, 1, 7, 1, padding=3))
        self.ups.apply(init_weights)
        self.conv_post.apply(init_weights)

    def forward(self, x):
        x = self.conv_pre(x)
        for i in range(self.num_upsamples):
            x = F.leaky_relu(x, LRELU_SLOPE)
            x = self.ups[i](x)
            xs = None
            for j in range(self.num_kernels):
                if xs is None:
                    xs = self.resblocks[i * self.num_kernels + j](x)
                else:
                    xs += self.resblocks[i * self.num_kernels + j](x)
            x = xs / self.num_kernels
        x = F.leaky_relu(x)
        x = self.conv_post(x)
        x = torch.tanh(x)

        return x

    def remove_weight_norm(self):
        print("Removing weight norm...")
        for layer in self.ups:
            remove_weight_norm(layer)
        for layer in self.resblocks:
            layer.remove_weight_norm()
        remove_weight_norm(self.conv_pre)
        remove_weight_norm(self.conv_post)