modules/wenet_extractor/transformer/positionwise_feed_forward.py

# This module is from [WeNet](https://github.com/wenet-e2e/wenet).

# ## Citations

# ```bibtex
# @inproceedings{yao2021wenet,
#   title={WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit},
#   author={Yao, Zhuoyuan and Wu, Di and Wang, Xiong and Zhang, Binbin and Yu, Fan and Yang, Chao and Peng, Zhendong and Chen, Xiaoyu and Xie, Lei and Lei, Xin},
#   booktitle={Proc. Interspeech},
#   year={2021},
#   address={Brno, Czech Republic },
#   organization={IEEE}
# }

# @article{zhang2022wenet,
#   title={WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit},
#   author={Zhang, Binbin and Wu, Di and Peng, Zhendong and Song, Xingchen and Yao, Zhuoyuan and Lv, Hang and Xie, Lei and Yang, Chao and Pan, Fuping and Niu, Jianwei},
#   journal={arXiv preprint arXiv:2203.15455},
#   year={2022}
# }
#

"""Positionwise feed forward layer definition."""

import torch


class PositionwiseFeedForward(torch.nn.Module):
    """Positionwise feed forward layer.

    FeedForward are appied on each position of the sequence.
    The output dim is same with the input dim.

    Args:
        idim (int): Input dimenstion.
        hidden_units (int): The number of hidden units.
        dropout_rate (float): Dropout rate.
        activation (torch.nn.Module): Activation function
    """

    def __init__(
        self,
        idim: int,
        hidden_units: int,
        dropout_rate: float,
        activation: torch.nn.Module = torch.nn.ReLU(),
    ):
        """Construct a PositionwiseFeedForward object."""
        super(PositionwiseFeedForward, self).__init__()
        self.w_1 = torch.nn.Linear(idim, hidden_units)
        self.activation = activation
        self.dropout = torch.nn.Dropout(dropout_rate)
        self.w_2 = torch.nn.Linear(hidden_units, idim)

    def forward(self, xs: torch.Tensor) -> torch.Tensor:
        """Forward function.

        Args:
            xs: input tensor (B, L, D)
        Returns:
            output tensor, (B, L, D)
        """
        return self.w_2(self.dropout(self.activation(self.w_1(xs))))