Spaces:
Runtime error
Runtime error
File size: 1,785 Bytes
e3dea0f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
from abc import ABC
import torch
from Layers.LayerNorm import LayerNorm
class VariancePredictor(torch.nn.Module, ABC):
def __init__(self, idim, n_layers=2, n_chans=384, kernel_size=3, bias=True, dropout_rate=0.5, ):
"""
Initilize duration predictor module.
Args:
idim (int): Input dimension.
n_layers (int, optional): Number of convolutional layers.
n_chans (int, optional): Number of channels of convolutional layers.
kernel_size (int, optional): Kernel size of convolutional layers.
dropout_rate (float, optional): Dropout rate.
"""
super().__init__()
self.conv = torch.nn.ModuleList()
for idx in range(n_layers):
in_chans = idim if idx == 0 else n_chans
self.conv += [
torch.nn.Sequential(torch.nn.Conv1d(in_chans, n_chans, kernel_size, stride=1, padding=(kernel_size - 1) // 2, bias=bias, ), torch.nn.ReLU(),
LayerNorm(n_chans, dim=1), torch.nn.Dropout(dropout_rate), )]
self.linear = torch.nn.Linear(n_chans, 1)
def forward(self, xs, x_masks=None):
"""
Calculate forward propagation.
Args:
xs (Tensor): Batch of input sequences (B, Tmax, idim).
x_masks (ByteTensor, optional):
Batch of masks indicating padded part (B, Tmax).
Returns:
Tensor: Batch of predicted sequences (B, Tmax, 1).
"""
xs = xs.transpose(1, -1) # (B, idim, Tmax)
for f in self.conv:
xs = f(xs) # (B, C, Tmax)
xs = self.linear(xs.transpose(1, 2)) # (B, Tmax, 1)
if x_masks is not None:
xs = xs.masked_fill(x_masks, 0.0)
return xs
|