mirror of https://github.com/coqui-ai/TTS.git
41 lines
1.3 KiB
Python
41 lines
1.3 KiB
Python
import torch
|
|
from torch import nn
|
|
|
|
from .normalization import LayerNorm
|
|
|
|
|
|
class DurationPredictor(nn.Module):
|
|
def __init__(self, in_channels, filter_channels, kernel_size, dropout_p):
|
|
super().__init__()
|
|
# class arguments
|
|
self.in_channels = in_channels
|
|
self.filter_channels = filter_channels
|
|
self.kernel_size = kernel_size
|
|
self.dropout_p = dropout_p
|
|
# layers
|
|
self.drop = nn.Dropout(dropout_p)
|
|
self.conv_1 = nn.Conv1d(in_channels,
|
|
filter_channels,
|
|
kernel_size,
|
|
padding=kernel_size // 2)
|
|
self.norm_1 = LayerNorm(filter_channels)
|
|
self.conv_2 = nn.Conv1d(filter_channels,
|
|
filter_channels,
|
|
kernel_size,
|
|
padding=kernel_size // 2)
|
|
self.norm_2 = LayerNorm(filter_channels)
|
|
# output layer
|
|
self.proj = nn.Conv1d(filter_channels, 1, 1)
|
|
|
|
def forward(self, x, x_mask):
|
|
x = self.conv_1(x * x_mask)
|
|
x = torch.relu(x)
|
|
x = self.norm_1(x)
|
|
x = self.drop(x)
|
|
x = self.conv_2(x * x_mask)
|
|
x = torch.relu(x)
|
|
x = self.norm_2(x)
|
|
x = self.drop(x)
|
|
x = self.proj(x * x_mask)
|
|
return x * x_mask
|