Source code for openspeech.modules.time_channel_separable_conv1d

# MIT License
#
# Copyright (c) 2021 Soohwan Kim and Sangchun Ha and Soyoung Cho
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

import torch.nn as nn
from torch import Tensor
from typing import Optional

from openspeech.modules.conv_base import BaseConv1d


class TimeChannelSeparableConv1d(BaseConv1d):
    r"""
    The total number of weights for a time-channel separable convolution block is K × cin + cin × cout weights. Since K is
    generally several times smaller than cout, most weights are
    concentrated in the pointwise convolution part.
    """
    def __init__(
            self,
            in_channels: int,
            out_channels: int,
            kernel_size: int = 1,
            padding: int = 0,
            groups: int = 1,
            bias: bool = True,
    ):
        super(TimeChannelSeparableConv1d, self).__init__()
        self.conv = nn.Conv1d(
            in_channels=in_channels,
            out_channels=out_channels,
            kernel_size=kernel_size,
            stride=1,
            dilation=1,
            padding=padding,
            groups=groups,
            bias=bias,
        )

    def forward(self, inputs: Tensor, input_lengths: Optional[Tensor] = None) -> Tensor:
        if input_lengths is None:
            return self.conv(inputs)
        else:
            return self.conv(inputs), self._get_sequence_lengths(input_lengths)