|
import math |
|
import torch |
|
from torch import nn |
|
from torch.nn import functional as F |
|
import modules |
|
import attentions |
|
from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d |
|
from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm |
|
from commons import init_weights |
|
import numpy as np |
|
import commons |
|
class TextEncoder256(nn.Module): |
|
def __init__( |
|
self, |
|
out_channels, |
|
hidden_channels, |
|
filter_channels, |
|
n_heads, |
|
n_layers, |
|
kernel_size, |
|
p_dropout, |
|
f0=True |
|
): |
|
super().__init__() |
|
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.emb_phone = nn.Linear(256, hidden_channels) |
|
self.lrelu=nn.LeakyReLU(0.1,inplace=True) |
|
if(f0==True): |
|
self.emb_pitch = nn.Embedding(256, hidden_channels) |
|
self.encoder = attentions.Encoder( |
|
hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout |
|
) |
|
self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1) |
|
|
|
def forward(self, phone, pitch, lengths): |
|
if(pitch==None): |
|
x = self.emb_phone(phone) |
|
else: |
|
x = self.emb_phone(phone) + self.emb_pitch(pitch) |
|
x = x * math.sqrt(self.hidden_channels) |
|
x=self.lrelu(x) |
|
x = torch.transpose(x, 1, -1) |
|
x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to( |
|
x.dtype |
|
) |
|
x = self.encoder(x * x_mask, x_mask) |
|
stats = self.proj(x) * x_mask |
|
|
|
m, logs = torch.split(stats, self.out_channels, dim=1) |
|
return m, logs, x_mask |
|
class ResidualCouplingBlock(nn.Module): |
|
def __init__( |
|
self, |
|
channels, |
|
hidden_channels, |
|
kernel_size, |
|
dilation_rate, |
|
n_layers, |
|
n_flows=4, |
|
gin_channels=0, |
|
): |
|
super().__init__() |
|
self.channels = channels |
|
self.hidden_channels = hidden_channels |
|
self.kernel_size = kernel_size |
|
self.dilation_rate = dilation_rate |
|
self.n_layers = n_layers |
|
self.n_flows = n_flows |
|
self.gin_channels = gin_channels |
|
|
|
self.flows = nn.ModuleList() |
|
for i in range(n_flows): |
|
self.flows.append( |
|
modules.ResidualCouplingLayer( |
|
channels, |
|
hidden_channels, |
|
kernel_size, |
|
dilation_rate, |
|
n_layers, |
|
gin_channels=gin_channels, |
|
mean_only=True, |
|
) |
|
) |
|
self.flows.append(modules.Flip()) |
|
|
|
def forward(self, x, x_mask, g=None, reverse=False): |
|
if not reverse: |
|
for flow in self.flows: |
|
x, _ = flow(x, x_mask, g=g, reverse=reverse) |
|
else: |
|
for flow in reversed(self.flows): |
|
x = flow(x, x_mask, g=g, reverse=reverse) |
|
return x |
|
|
|
def remove_weight_norm(self): |
|
for i in range(self.n_flows): |
|
self.flows[i * 2].remove_weight_norm() |
|
class PosteriorEncoder(nn.Module): |
|
def __init__( |
|
self, |
|
in_channels, |
|
out_channels, |
|
hidden_channels, |
|
kernel_size, |
|
dilation_rate, |
|
n_layers, |
|
gin_channels=0, |
|
): |
|
super().__init__() |
|
self.in_channels = in_channels |
|
self.out_channels = out_channels |
|
self.hidden_channels = hidden_channels |
|
self.kernel_size = kernel_size |
|
self.dilation_rate = dilation_rate |
|
self.n_layers = n_layers |
|
self.gin_channels = gin_channels |
|
|
|
self.pre = nn.Conv1d(in_channels, hidden_channels, 1) |
|
self.enc = modules.WN( |
|
hidden_channels, |
|
kernel_size, |
|
dilation_rate, |
|
n_layers, |
|
gin_channels=gin_channels, |
|
) |
|
self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1) |
|
|
|
def forward(self, x, x_lengths, g=None): |
|
x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to( |
|
x.dtype |
|
) |
|
x = self.pre(x) * x_mask |
|
x = self.enc(x, x_mask, g=g) |
|
stats = self.proj(x) * x_mask |
|
m, logs = torch.split(stats, self.out_channels, dim=1) |
|
z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask |
|
return z, m, logs, x_mask |
|
|
|
def remove_weight_norm(self): |
|
self.enc.remove_weight_norm() |
|
class Generator(torch.nn.Module): |
|
def __init__( |
|
self, |
|
initial_channel, |
|
resblock, |
|
resblock_kernel_sizes, |
|
resblock_dilation_sizes, |
|
upsample_rates, |
|
upsample_initial_channel, |
|
upsample_kernel_sizes, |
|
gin_channels=0, |
|
): |
|
super(Generator, self).__init__() |
|
self.num_kernels = len(resblock_kernel_sizes) |
|
self.num_upsamples = len(upsample_rates) |
|
self.conv_pre = Conv1d( |
|
initial_channel, upsample_initial_channel, 7, 1, padding=3 |
|
) |
|
resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2 |
|
|
|
self.ups = nn.ModuleList() |
|
for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)): |
|
self.ups.append( |
|
weight_norm( |
|
ConvTranspose1d( |
|
upsample_initial_channel // (2**i), |
|
upsample_initial_channel // (2 ** (i + 1)), |
|
k, |
|
u, |
|
padding=(k - u) // 2, |
|
) |
|
) |
|
) |
|
|
|
self.resblocks = nn.ModuleList() |
|
for i in range(len(self.ups)): |
|
ch = upsample_initial_channel // (2 ** (i + 1)) |
|
for j, (k, d) in enumerate( |
|
zip(resblock_kernel_sizes, resblock_dilation_sizes) |
|
): |
|
self.resblocks.append(resblock(ch, k, d)) |
|
|
|
self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False) |
|
self.ups.apply(init_weights) |
|
|
|
if gin_channels != 0: |
|
self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1) |
|
|
|
def forward(self, x, g=None): |
|
x = self.conv_pre(x) |
|
if g is not None: |
|
x = x + self.cond(g) |
|
|
|
for i in range(self.num_upsamples): |
|
x = F.leaky_relu(x, modules.LRELU_SLOPE) |
|
x = self.ups[i](x) |
|
xs = None |
|
for j in range(self.num_kernels): |
|
if xs is None: |
|
xs = self.resblocks[i * self.num_kernels + j](x) |
|
else: |
|
xs += self.resblocks[i * self.num_kernels + j](x) |
|
x = xs / self.num_kernels |
|
x = F.leaky_relu(x) |
|
x = self.conv_post(x) |
|
x = torch.tanh(x) |
|
|
|
return x |
|
|
|
def remove_weight_norm(self): |
|
for l in self.ups: |
|
remove_weight_norm(l) |
|
for l in self.resblocks: |
|
l.remove_weight_norm() |
|
class SynthesizerTrnNoF0256(nn.Module): |
|
""" |
|
Synthesizer for Training |
|
""" |
|
|
|
def __init__( |
|
self, |
|
spec_channels, |
|
segment_size, |
|
inter_channels, |
|
hidden_channels, |
|
filter_channels, |
|
n_heads, |
|
n_layers, |
|
kernel_size, |
|
p_dropout, |
|
resblock, |
|
resblock_kernel_sizes, |
|
resblock_dilation_sizes, |
|
upsample_rates, |
|
upsample_initial_channel, |
|
upsample_kernel_sizes, |
|
gin_channels |
|
): |
|
|
|
super().__init__() |
|
self.spec_channels = spec_channels |
|
self.inter_channels = inter_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.resblock = resblock |
|
self.resblock_kernel_sizes = resblock_kernel_sizes |
|
self.resblock_dilation_sizes = resblock_dilation_sizes |
|
self.upsample_rates = upsample_rates |
|
self.upsample_initial_channel = upsample_initial_channel |
|
self.upsample_kernel_sizes = upsample_kernel_sizes |
|
self.segment_size = segment_size |
|
self.gin_channels = gin_channels |
|
|
|
self.enc_p = TextEncoder256( |
|
inter_channels, |
|
hidden_channels, |
|
filter_channels, |
|
n_heads, |
|
n_layers, |
|
kernel_size, |
|
p_dropout, |
|
f0=False, |
|
) |
|
self.dec = Generator( |
|
inter_channels, |
|
resblock, |
|
resblock_kernel_sizes, |
|
resblock_dilation_sizes, |
|
upsample_rates, |
|
upsample_initial_channel, |
|
upsample_kernel_sizes, |
|
gin_channels=gin_channels, |
|
) |
|
self.enc_q = PosteriorEncoder( |
|
spec_channels, |
|
inter_channels, |
|
hidden_channels, |
|
5, |
|
1, |
|
16, |
|
gin_channels=gin_channels, |
|
) |
|
self.flow = ResidualCouplingBlock( |
|
inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels |
|
) |
|
|
|
def remove_weight_norm(self): |
|
self.dec.remove_weight_norm() |
|
self.flow.remove_weight_norm() |
|
self.enc_q.remove_weight_norm() |
|
|
|
def infer(self, phone, phone_lengths, max_len=None): |
|
m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths) |
|
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66) * x_mask |
|
z = self.flow(z_p, x_mask, g=None, reverse=True) |
|
o = self.dec((z * x_mask)[:, :, :max_len], g=None) |
|
return o, x_mask, (z, z_p, m_p, logs_p) |
|
|
