Fork of https://github.com/alokprasad/fastspeech_squeezewave to also fix denoising in squeezewave
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
36 lines
1.3 KiB
36 lines
1.3 KiB
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
|