DeepLearningExamples/CUDA-Optimized/FastSpeech/tacotron2/layers.py

# BSD 3-Clause License

# Copyright (c) 2018-2020, NVIDIA Corporation
# All rights reserved.

# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:

# * Redistributions of source code must retain the above copyright notice, this
#   list of conditions and the following disclaimer.

# * Redistributions in binary form must reproduce the above copyright notice,
#   this list of conditions and the following disclaimer in the documentation
#   and/or other materials provided with the distribution.

# * Neither the name of the copyright holder nor the names of its
#   contributors may be used to endorse or promote products derived from
#   this software without specific prior written permission.

# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

"""https://github.com/NVIDIA/tacotron2"""

import torch
from librosa.filters import mel as librosa_mel_fn


class LinearNorm(torch.nn.Module):
    def __init__(self, in_dim, out_dim, bias=True, w_init_gain='linear'):
        super(LinearNorm, self).__init__()
        self.linear_layer = torch.nn.Linear(in_dim, out_dim, bias=bias)

        torch.nn.init.xavier_uniform_(
            self.linear_layer.weight,
            gain=torch.nn.init.calculate_gain(w_init_gain))

    def forward(self, x):
        return self.linear_layer(x)


class ConvNorm(torch.nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1,
                 padding=None, dilation=1, bias=True, w_init_gain='linear'):
        super(ConvNorm, self).__init__()
        if padding is None:
            assert(kernel_size % 2 == 1)
            padding = int(dilation * (kernel_size - 1) / 2)

        self.conv = torch.nn.Conv1d(in_channels, out_channels,
                                    kernel_size=kernel_size, stride=stride,
                                    padding=padding, dilation=dilation,
                                    bias=bias)

        torch.nn.init.xavier_uniform_(
            self.conv.weight, gain=torch.nn.init.calculate_gain(w_init_gain))

    def forward(self, signal):
        conv_signal = self.conv(signal)
        return conv_signal