mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-16 04:32:19 +00:00
458 lines
14 KiB
Python
458 lines
14 KiB
Python
import logging
|
|
|
|
from typing import List
|
|
import torch
|
|
import torch.nn.functional as F
|
|
import torch.nn as nn
|
|
from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
|
|
from torch.nn.utils import remove_weight_norm, spectral_norm
|
|
from torch.nn.utils.parametrizations import weight_norm
|
|
|
|
LRELU_SLOPE = 0.1
|
|
|
|
|
|
def init_weights(m, mean=0.0, std=0.01):
|
|
classname = m.__class__.__name__
|
|
if classname.find("Conv") != -1:
|
|
m.weight.data.normal_(mean, std)
|
|
|
|
|
|
def apply_weight_norm(m):
|
|
classname = m.__class__.__name__
|
|
if classname.find("Conv") != -1:
|
|
weight_norm(m)
|
|
|
|
|
|
def get_padding(kernel_size, dilation=1):
|
|
return int((kernel_size * dilation - dilation) / 2)
|
|
|
|
|
|
class ResBlock1(torch.nn.Module):
|
|
def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
|
|
super(ResBlock1, self).__init__()
|
|
self.convs1 = nn.ModuleList(
|
|
[
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=dilation[0],
|
|
padding=get_padding(kernel_size, dilation[0]),
|
|
)
|
|
),
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=dilation[1],
|
|
padding=get_padding(kernel_size, dilation[1]),
|
|
)
|
|
),
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=dilation[2],
|
|
padding=get_padding(kernel_size, dilation[2]),
|
|
)
|
|
),
|
|
]
|
|
)
|
|
self.convs1.apply(init_weights)
|
|
|
|
self.convs2 = nn.ModuleList(
|
|
[
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=1,
|
|
padding=get_padding(kernel_size, 1),
|
|
)
|
|
),
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=1,
|
|
padding=get_padding(kernel_size, 1),
|
|
)
|
|
),
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=1,
|
|
padding=get_padding(kernel_size, 1),
|
|
)
|
|
),
|
|
]
|
|
)
|
|
self.convs2.apply(init_weights)
|
|
|
|
def forward(self, x):
|
|
for c1, c2 in zip(self.convs1, self.convs2):
|
|
xt = F.leaky_relu(x, LRELU_SLOPE)
|
|
xt = c1(xt)
|
|
xt = F.leaky_relu(xt, LRELU_SLOPE)
|
|
xt = c2(xt)
|
|
x = xt + x
|
|
return x
|
|
|
|
def remove_weight_norm(self):
|
|
for l in self.convs1:
|
|
remove_weight_norm(l)
|
|
for l in self.convs2:
|
|
remove_weight_norm(l)
|
|
|
|
|
|
class ResBlock2(torch.nn.Module):
|
|
def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
|
|
super(ResBlock2, self).__init__()
|
|
self.convs = nn.ModuleList(
|
|
[
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=dilation[0],
|
|
padding=get_padding(kernel_size, dilation[0]),
|
|
)
|
|
),
|
|
weight_norm(
|
|
Conv1d(
|
|
channels,
|
|
channels,
|
|
kernel_size,
|
|
1,
|
|
dilation=dilation[1],
|
|
padding=get_padding(kernel_size, dilation[1]),
|
|
)
|
|
),
|
|
]
|
|
)
|
|
self.convs.apply(init_weights)
|
|
|
|
def forward(self, x):
|
|
for c in self.convs:
|
|
xt = F.leaky_relu(x, LRELU_SLOPE)
|
|
xt = c(xt)
|
|
x = xt + x
|
|
return x
|
|
|
|
def remove_weight_norm(self):
|
|
for l in self.convs:
|
|
remove_weight_norm(l)
|
|
|
|
|
|
class Generator(torch.nn.Module):
|
|
def __init__(
|
|
self,
|
|
in_channels: int = 80,
|
|
upsample_initial_channel: int = 512,
|
|
upsample_rates: List[int] = [8, 8, 2, 2],
|
|
upsample_kernel_sizes: List[int] = [16, 16, 4, 4],
|
|
resblock_version: str = "1",
|
|
resblock_kernel_sizes: List[int] = [3, 7, 11],
|
|
resblock_dilation_sizes: List[List[int]] = [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
|
|
):
|
|
super(Generator, self).__init__()
|
|
self.num_kernels = len(resblock_kernel_sizes)
|
|
self.num_upsamples = len(upsample_rates)
|
|
self.conv_pre = weight_norm(
|
|
Conv1d(in_channels, upsample_initial_channel, 7, 1, padding=3)
|
|
)
|
|
resblock = ResBlock1 if resblock_version == "1" else 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(channels=ch, kernel_size=k, dilation=d))
|
|
|
|
self.conv_post = weight_norm(Conv1d(ch, 1, 7, 1, padding=3))
|
|
self.ups.apply(init_weights)
|
|
self.conv_post.apply(init_weights)
|
|
|
|
def forward(self, x):
|
|
x = self.conv_pre(x)
|
|
for i in range(self.num_upsamples):
|
|
x = F.leaky_relu(x, 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):
|
|
logging.info("Removing weight norm...")
|
|
for l in self.ups:
|
|
remove_weight_norm(l)
|
|
for l in self.resblocks:
|
|
l.remove_weight_norm()
|
|
remove_weight_norm(self.conv_pre)
|
|
remove_weight_norm(self.conv_post)
|
|
|
|
|
|
class DiscriminatorP(torch.nn.Module):
|
|
def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
|
|
super(DiscriminatorP, self).__init__()
|
|
self.period = period
|
|
norm_f = weight_norm if use_spectral_norm == False else spectral_norm
|
|
self.convs = nn.ModuleList(
|
|
[
|
|
norm_f(
|
|
Conv2d(
|
|
1,
|
|
32,
|
|
(kernel_size, 1),
|
|
(stride, 1),
|
|
padding=(get_padding(5, 1), 0),
|
|
)
|
|
),
|
|
norm_f(
|
|
Conv2d(
|
|
32,
|
|
128,
|
|
(kernel_size, 1),
|
|
(stride, 1),
|
|
padding=(get_padding(5, 1), 0),
|
|
)
|
|
),
|
|
norm_f(
|
|
Conv2d(
|
|
128,
|
|
512,
|
|
(kernel_size, 1),
|
|
(stride, 1),
|
|
padding=(get_padding(5, 1), 0),
|
|
)
|
|
),
|
|
norm_f(
|
|
Conv2d(
|
|
512,
|
|
1024,
|
|
(kernel_size, 1),
|
|
(stride, 1),
|
|
padding=(get_padding(5, 1), 0),
|
|
)
|
|
),
|
|
norm_f(Conv2d(1024, 1024, (kernel_size, 1), 1, padding=(2, 0))),
|
|
]
|
|
)
|
|
self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
|
|
|
|
def forward(self, x):
|
|
fmap = []
|
|
|
|
# 1d to 2d
|
|
b, c, t = x.shape
|
|
if t % self.period != 0: # pad first
|
|
n_pad = self.period - (t % self.period)
|
|
x = F.pad(x, (0, n_pad), "reflect")
|
|
t = t + n_pad
|
|
x = x.view(b, c, t // self.period, self.period)
|
|
|
|
for l in self.convs:
|
|
x = l(x)
|
|
x = F.leaky_relu(x, LRELU_SLOPE)
|
|
fmap.append(x)
|
|
x = self.conv_post(x)
|
|
fmap.append(x)
|
|
x = torch.flatten(x, 1, -1)
|
|
|
|
return x, fmap
|
|
|
|
|
|
class MultiPeriodDiscriminator(torch.nn.Module):
|
|
def __init__(self):
|
|
super(MultiPeriodDiscriminator, self).__init__()
|
|
self.discriminators = nn.ModuleList(
|
|
[
|
|
DiscriminatorP(2),
|
|
DiscriminatorP(3),
|
|
DiscriminatorP(5),
|
|
DiscriminatorP(7),
|
|
DiscriminatorP(11),
|
|
]
|
|
)
|
|
|
|
def forward(self, y, y_hat):
|
|
y_d_rs = []
|
|
y_d_gs = []
|
|
fmap_rs = []
|
|
fmap_gs = []
|
|
for i, d in enumerate(self.discriminators):
|
|
y_d_r, fmap_r = d(y)
|
|
y_d_g, fmap_g = d(y_hat)
|
|
y_d_rs.append(y_d_r)
|
|
fmap_rs.append(fmap_r)
|
|
y_d_gs.append(y_d_g)
|
|
fmap_gs.append(fmap_g)
|
|
|
|
return y_d_rs, y_d_gs, fmap_rs, fmap_gs
|
|
|
|
|
|
class DiscriminatorS(torch.nn.Module):
|
|
def __init__(self, use_spectral_norm=False):
|
|
super(DiscriminatorS, self).__init__()
|
|
norm_f = weight_norm if use_spectral_norm == False else spectral_norm
|
|
self.convs = nn.ModuleList(
|
|
[
|
|
norm_f(Conv1d(1, 128, 15, 1, padding=7)),
|
|
norm_f(Conv1d(128, 128, 41, 2, groups=4, padding=20)),
|
|
norm_f(Conv1d(128, 256, 41, 2, groups=16, padding=20)),
|
|
norm_f(Conv1d(256, 512, 41, 4, groups=16, padding=20)),
|
|
norm_f(Conv1d(512, 1024, 41, 4, groups=16, padding=20)),
|
|
norm_f(Conv1d(1024, 1024, 41, 1, groups=16, padding=20)),
|
|
norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
|
|
]
|
|
)
|
|
self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
|
|
|
|
def forward(self, x):
|
|
fmap = []
|
|
for l in self.convs:
|
|
x = l(x)
|
|
x = F.leaky_relu(x, LRELU_SLOPE)
|
|
fmap.append(x)
|
|
x = self.conv_post(x)
|
|
fmap.append(x)
|
|
x = torch.flatten(x, 1, -1)
|
|
|
|
return x, fmap
|
|
|
|
|
|
class MultiScaleDiscriminator(torch.nn.Module):
|
|
def __init__(self):
|
|
super(MultiScaleDiscriminator, self).__init__()
|
|
self.discriminators = nn.ModuleList(
|
|
[
|
|
DiscriminatorS(use_spectral_norm=True),
|
|
DiscriminatorS(),
|
|
DiscriminatorS(),
|
|
]
|
|
)
|
|
self.meanpools = nn.ModuleList(
|
|
[AvgPool1d(4, 2, padding=2), AvgPool1d(4, 2, padding=2)]
|
|
)
|
|
|
|
def forward(self, y, y_hat):
|
|
y_d_rs = []
|
|
y_d_gs = []
|
|
fmap_rs = []
|
|
fmap_gs = []
|
|
for i, d in enumerate(self.discriminators):
|
|
if i != 0:
|
|
y = self.meanpools[i - 1](y)
|
|
y_hat = self.meanpools[i - 1](y_hat)
|
|
y_d_r, fmap_r = d(y)
|
|
y_d_g, fmap_g = d(y_hat)
|
|
y_d_rs.append(y_d_r)
|
|
fmap_rs.append(fmap_r)
|
|
y_d_gs.append(y_d_g)
|
|
fmap_gs.append(fmap_g)
|
|
|
|
return y_d_rs, y_d_gs, fmap_rs, fmap_gs
|
|
|
|
|
|
def feature_loss(fmap_r, fmap_g):
|
|
loss = 0
|
|
for dr, dg in zip(fmap_r, fmap_g):
|
|
for rl, gl in zip(dr, dg):
|
|
if rl.shape[2] < gl.shape[2]:
|
|
gl = gl[:, :, 0 : rl.shape[2], ...]
|
|
elif gl.shape[2] < rl.shape[2]:
|
|
rl = rl[:, :, 0 : gl.shape[2], ...]
|
|
loss += torch.mean(torch.abs(rl - gl))
|
|
return loss * 2
|
|
|
|
|
|
def discriminator_loss(disc_real_outputs, disc_generated_outputs):
|
|
loss = 0
|
|
r_losses = []
|
|
g_losses = []
|
|
for dr, dg in zip(disc_real_outputs, disc_generated_outputs):
|
|
r_loss = torch.mean((1 - dr) ** 2)
|
|
g_loss = torch.mean(dg**2)
|
|
loss += r_loss + g_loss
|
|
r_losses.append(r_loss.item())
|
|
g_losses.append(g_loss.item())
|
|
|
|
return loss, r_losses, g_losses
|
|
|
|
|
|
def generator_loss(disc_outputs):
|
|
loss = 0
|
|
gen_losses = []
|
|
for dg in disc_outputs:
|
|
l = torch.mean((1 - dg) ** 2)
|
|
gen_losses.append(l)
|
|
loss += l
|
|
return loss, gen_losses
|
|
|
|
|
|
class HiFiGAN(torch.nn.Module):
|
|
def __init__(
|
|
self,
|
|
in_channels: int = 80,
|
|
upsample_initial_channel: int = 512,
|
|
upsample_rates: List[int] = [8, 8, 2, 2],
|
|
upsample_kernel_sizes: List[int] = [16, 16, 4, 4],
|
|
resblock_version: str = "1",
|
|
resblock_kernel_sizes: List[int] = [3, 7, 11],
|
|
resblock_dilation_sizes: List[List[int]] = [[1, 3, 5], [1, 3, 5], [1, 3, 5]],
|
|
):
|
|
super(HiFiGAN, self).__init__()
|
|
self.generator = Generator(
|
|
in_channels=in_channels,
|
|
upsample_initial_channel=upsample_initial_channel,
|
|
upsample_rates=upsample_rates,
|
|
upsample_kernel_sizes=upsample_kernel_sizes,
|
|
resblock_version=resblock_version,
|
|
resblock_kernel_sizes=resblock_kernel_sizes,
|
|
resblock_dilation_sizes=resblock_dilation_sizes,
|
|
)
|
|
self.mpd = MultiPeriodDiscriminator()
|
|
self.msd = MultiScaleDiscriminator()
|
|
|
|
def forward(self, x):
|
|
return self.generator(x)
|