File size: 4,838 Bytes
67c46fd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#!/usr/bin/env python3
# -*- coding: utf-8 -*-

# Copyright 2019 Tomoki Hayashi
#  Apache 2.0  (http://www.apache.org/licenses/LICENSE-2.0)

"""Layer modules for FFT block in FastSpeech (Feed-forward Transformer)."""

import torch


class MultiLayeredConv1d(torch.nn.Module):
    """Multi-layered conv1d for Transformer block.

    This is a module of multi-leyered conv1d designed
    to replace positionwise feed-forward network
    in Transforner block, which is introduced in
    `FastSpeech: Fast, Robust and Controllable Text to Speech`_.

    .. _`FastSpeech: Fast, Robust and Controllable Text to Speech`:
        https://arxiv.org/pdf/1905.09263.pdf

    """

    def __init__(self, in_chans, hidden_chans, kernel_size, dropout_rate):
        """Initialize MultiLayeredConv1d module.

        Args:
            in_chans (int): Number of input channels.
            hidden_chans (int): Number of hidden channels.
            kernel_size (int): Kernel size of conv1d.
            dropout_rate (float): Dropout rate.

        """
        super(MultiLayeredConv1d, self).__init__()
        self.w_1 = torch.nn.Conv1d(
            in_chans,
            hidden_chans,
            kernel_size,
            stride=1,
            padding=(kernel_size - 1) // 2,
        )
        self.w_2 = torch.nn.Conv1d(
            hidden_chans,
            in_chans,
            kernel_size,
            stride=1,
            padding=(kernel_size - 1) // 2,
        )
        self.dropout = torch.nn.Dropout(dropout_rate)

    def forward(self, x):
        """Calculate forward propagation.

        Args:
            x (torch.Tensor): Batch of input tensors (B, T, in_chans).

        Returns:
            torch.Tensor: Batch of output tensors (B, T, hidden_chans).

        """
        x = torch.relu(self.w_1(x.transpose(-1, 1))).transpose(-1, 1)
        return self.w_2(self.dropout(x).transpose(-1, 1)).transpose(-1, 1)


class FsmnFeedForward(torch.nn.Module):
    """Position-wise feed forward for FSMN blocks.

    This is a module of multi-leyered conv1d designed
    to replace position-wise feed-forward network
    in FSMN block.
    """

    def __init__(self, in_chans, hidden_chans, out_chans, kernel_size, dropout_rate):
        """Initialize FsmnFeedForward module.

        Args:
            in_chans (int): Number of input channels.
            hidden_chans (int): Number of hidden channels.
            out_chans (int): Number of output channels.
            kernel_size (int): Kernel size of conv1d.
            dropout_rate (float): Dropout rate.

        """
        super(FsmnFeedForward, self).__init__()
        self.w_1 = torch.nn.Conv1d(
            in_chans,
            hidden_chans,
            kernel_size,
            stride=1,
            padding=(kernel_size - 1) // 2,
        )
        self.w_2 = torch.nn.Conv1d(
            hidden_chans,
            out_chans,
            kernel_size,
            stride=1,
            padding=(kernel_size - 1) // 2,
            bias=False,
        )
        self.norm = torch.nn.LayerNorm(hidden_chans)
        self.dropout = torch.nn.Dropout(dropout_rate)

    def forward(self, x, ilens=None):
        """Calculate forward propagation.

        Args:
            x (torch.Tensor): Batch of input tensors (B, T, in_chans).

        Returns:
            torch.Tensor: Batch of output tensors (B, T, out_chans).

        """
        x = torch.relu(self.w_1(x.transpose(-1, 1))).transpose(-1, 1)
        return (
            self.w_2(self.norm(self.dropout(x)).transpose(-1, 1)).transpose(-1, 1),
            ilens,
        )


class Conv1dLinear(torch.nn.Module):
    """Conv1D + Linear for Transformer block.

    A variant of MultiLayeredConv1d, which replaces second conv-layer to linear.

    """

    def __init__(self, in_chans, hidden_chans, kernel_size, dropout_rate):
        """Initialize Conv1dLinear module.

        Args:
            in_chans (int): Number of input channels.
            hidden_chans (int): Number of hidden channels.
            kernel_size (int): Kernel size of conv1d.
            dropout_rate (float): Dropout rate.

        """
        super(Conv1dLinear, self).__init__()
        self.w_1 = torch.nn.Conv1d(
            in_chans,
            hidden_chans,
            kernel_size,
            stride=1,
            padding=(kernel_size - 1) // 2,
        )
        self.w_2 = torch.nn.Linear(hidden_chans, in_chans)
        self.dropout = torch.nn.Dropout(dropout_rate)

    def forward(self, x):
        """Calculate forward propagation.

        Args:
            x (torch.Tensor): Batch of input tensors (B, T, in_chans).

        Returns:
            torch.Tensor: Batch of output tensors (B, T, hidden_chans).

        """
        x = torch.relu(self.w_1(x.transpose(-1, 1))).transpose(-1, 1)
        return self.w_2(self.dropout(x))