File size: 7,832 Bytes
fe781a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
from typing import Optional, Tuple

import torch
from torch import nn
from torch.nn.utils import weight_norm, remove_weight_norm


class ConvNeXtBlock(nn.Module):
    """ConvNeXt Block adapted from https://github.com/facebookresearch/ConvNeXt to 1D audio signal.

    Args:
        dim (int): Number of input channels.
        intermediate_dim (int): Dimensionality of the intermediate layer.
        layer_scale_init_value (float, optional): Initial value for the layer scale. None means no scaling.
            Defaults to None.
        adanorm_num_embeddings (int, optional): Number of embeddings for AdaLayerNorm.
            None means non-conditional LayerNorm. Defaults to None.
    """

    def __init__(
        self,
        dim: int,
        intermediate_dim: int,
        layer_scale_init_value: float,
        adanorm_num_embeddings: Optional[int] = None,
    ):
        super().__init__()
        self.dwconv = nn.Conv1d(dim, dim, kernel_size=7, padding=3, groups=dim)  # depthwise conv
        self.adanorm = adanorm_num_embeddings is not None
        if adanorm_num_embeddings:
            self.norm = AdaLayerNorm(adanorm_num_embeddings, dim, eps=1e-6)
        else:
            self.norm = nn.LayerNorm(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, intermediate_dim)  # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(intermediate_dim, dim)
        self.gamma = (
            nn.Parameter(layer_scale_init_value * torch.ones(dim), requires_grad=True)
            if layer_scale_init_value > 0
            else None
        )

    def forward(self, x: torch.Tensor, cond_embedding_id: Optional[torch.Tensor] = None) -> torch.Tensor:
        residual = x
        x = self.dwconv(x)
        x = x.transpose(1, 2)  # (B, C, T) -> (B, T, C)
        if self.adanorm:
            assert cond_embedding_id is not None
            x = self.norm(x, cond_embedding_id)
        else:
            x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma is not None:
            x = self.gamma * x
        x = x.transpose(1, 2)  # (B, T, C) -> (B, C, T)

        x = residual + x
        return x


class AdaLayerNorm(nn.Module):
    """
    Adaptive Layer Normalization module with learnable embeddings per `num_embeddings` classes

    Args:
        num_embeddings (int): Number of embeddings.
        embedding_dim (int): Dimension of the embeddings.
    """

    def __init__(self, num_embeddings: int, embedding_dim: int, eps: float = 1e-6):
        super().__init__()
        self.eps = eps
        self.dim = embedding_dim
        self.scale = nn.Embedding(num_embeddings=num_embeddings, embedding_dim=embedding_dim)
        self.shift = nn.Embedding(num_embeddings=num_embeddings, embedding_dim=embedding_dim)
        torch.nn.init.ones_(self.scale.weight)
        torch.nn.init.zeros_(self.shift.weight)

    def forward(self, x: torch.Tensor, cond_embedding_id: torch.Tensor) -> torch.Tensor:
        scale = self.scale(cond_embedding_id)
        shift = self.shift(cond_embedding_id)
        x = nn.functional.layer_norm(x, (self.dim,), eps=self.eps)
        x = x * scale + shift
        return x


class ResBlock1(nn.Module):
    """
    ResBlock adapted from HiFi-GAN V1 (https://github.com/jik876/hifi-gan) with dilated 1D convolutions,
    but without upsampling layers.

    Args:
        dim (int): Number of input channels.
        kernel_size (int, optional): Size of the convolutional kernel. Defaults to 3.
        dilation (tuple[int], optional): Dilation factors for the dilated convolutions.
            Defaults to (1, 3, 5).
        lrelu_slope (float, optional): Negative slope of the LeakyReLU activation function.
            Defaults to 0.1.
        layer_scale_init_value (float, optional): Initial value for the layer scale. None means no scaling.
            Defaults to None.
    """

    def __init__(
        self,
        dim: int,
        kernel_size: int = 3,
        dilation: Tuple[int, int, int] = (1, 3, 5),
        lrelu_slope: float = 0.1,
        layer_scale_init_value: Optional[float] = None,
    ):
        super().__init__()
        self.lrelu_slope = lrelu_slope
        self.convs1 = nn.ModuleList(
            [
                weight_norm(
                    nn.Conv1d(
                        dim,
                        dim,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=self.get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    nn.Conv1d(
                        dim,
                        dim,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=self.get_padding(kernel_size, dilation[1]),
                    )
                ),
                weight_norm(
                    nn.Conv1d(
                        dim,
                        dim,
                        kernel_size,
                        1,
                        dilation=dilation[2],
                        padding=self.get_padding(kernel_size, dilation[2]),
                    )
                ),
            ]
        )

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

        self.gamma = nn.ParameterList(
            [
                nn.Parameter(layer_scale_init_value * torch.ones(dim, 1), requires_grad=True)
                if layer_scale_init_value is not None
                else None,
                nn.Parameter(layer_scale_init_value * torch.ones(dim, 1), requires_grad=True)
                if layer_scale_init_value is not None
                else None,
                nn.Parameter(layer_scale_init_value * torch.ones(dim, 1), requires_grad=True)
                if layer_scale_init_value is not None
                else None,
            ]
        )

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        for c1, c2, gamma in zip(self.convs1, self.convs2, self.gamma):
            xt = torch.nn.functional.leaky_relu(x, negative_slope=self.lrelu_slope)
            xt = c1(xt)
            xt = torch.nn.functional.leaky_relu(xt, negative_slope=self.lrelu_slope)
            xt = c2(xt)
            if gamma is not None:
                xt = gamma * xt
            x = xt + x
        return x

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

    @staticmethod
    def get_padding(kernel_size: int, dilation: int = 1) -> int:
        return int((kernel_size * dilation - dilation) / 2)


def safe_log(x: torch.Tensor, clip_val: float = 1e-7) -> torch.Tensor:
    """
    Computes the element-wise logarithm of the input tensor with clipping to avoid near-zero values.

    Args:
        x (Tensor): Input tensor.
        clip_val (float, optional): Minimum value to clip the input tensor. Defaults to 1e-7.

    Returns:
        Tensor: Element-wise logarithm of the input tensor with clipping applied.
    """
    return torch.log(torch.clip(x, min=clip_val))


def symlog(x: torch.Tensor) -> torch.Tensor:
    return torch.sign(x) * torch.log1p(x.abs())


def symexp(x: torch.Tensor) -> torch.Tensor:
    return torch.sign(x) * (torch.exp(x.abs()) - 1)