Spaces:
Runtime error
Runtime error
File size: 1,664 Bytes
d492199 | 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 55 56 | import torch
from torch import nn
from torch.nn import functional as F
import math
from .encoder import Encoder
from . import commons
class TextEncoder(nn.Module):
def __init__(
self,
n_vocab,
out_channels,
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
gin_channels=0,
):
super().__init__()
self.n_vocab = n_vocab
self.out_channels = out_channels
self.hidden_channels = hidden_channels
self.filter_channels = filter_channels
self.n_heads = n_heads
self.n_layers = n_layers
self.kernel_size = kernel_size
self.p_dropout = p_dropout
self.gin_channels = gin_channels
self.emb = nn.Embedding(n_vocab, hidden_channels)
nn.init.normal_(self.emb.weight, 0.0, hidden_channels**-0.5)
self.encoder = Encoder(
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
gin_channels=self.gin_channels,
)
self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
def forward(self, x, x_lengths, g=None):
x = self.emb(x) * math.sqrt(self.hidden_channels) # [b, t, h]
x = torch.transpose(x, 1, -1) # [b, h, t]
x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
x.dtype
)
x = self.encoder(x * x_mask, x_mask, g=g)
stats = self.proj(x) * x_mask
m, logs = torch.split(stats, self.out_channels, dim=1)
return x, m, logs, x_mask |