Source code for openspeech.modules.conformer_feed_forward_module

# 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 openspeech.modules.swish import Swish
from openspeech.modules.wrapper import Linear


class FeedForwardModule(nn.Module):
    r"""
    Conformer Feed Forward Module follow pre-norm residual units and apply layer normalization within the residual unit
    and on the input before the first linear layer. This module also apply Swish activation and dropout, which helps
    regularizing the network.

    Args:
        encoder_dim (int): Dimension of conformer encoders
        expansion_factor (int): Expansion factor of feed forward module.
        dropout_p (float): Ratio of dropout

    Inputs: inputs
        - **inputs** (batch, time, dim): Tensor contains input sequences

    Outputs: outputs
        - **outputs** (batch, time, dim): Tensor produces by feed forward module.
    """
    def __init__(
            self,
            encoder_dim: int = 512,
            expansion_factor: int = 4,
            dropout_p: float = 0.1,
    ) -> None:
        super(FeedForwardModule, self).__init__()
        self.sequential = nn.Sequential(
            Linear(encoder_dim, encoder_dim * expansion_factor, bias=True),
            Swish(),
            nn.Dropout(p=dropout_p),
            Linear(encoder_dim * expansion_factor, encoder_dim, bias=True),
            nn.Dropout(p=dropout_p),
        )

    def forward(self, inputs: Tensor) -> Tensor:
        r"""
        Forward propagate of conformer's feed-forward module.

        Inputs: inputs
            - **inputs** (batch, time, dim): Tensor contains input sequences

        Outputs: outputs
            - **outputs** (batch, time, dim): Tensor produces by feed forward module.
        """
        return self.sequential(inputs)