1406 lines
48 KiB
Python
1406 lines
48 KiB
Python
import math
|
||
import torch
|
||
from torch import nn
|
||
from torch.nn import functional as F
|
||
from . import modules
|
||
from . import attentions
|
||
from .commons import generate_path, init_weights, get_padding, rand_slice_segments, sequence_mask, slice_segments2
|
||
from torch.nn import Conv1d, ConvTranspose1d, Conv2d
|
||
from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
|
||
import numpy as np
|
||
import monotonic_align
|
||
|
||
|
||
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) # pitch 256
|
||
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) # [b, t, h]
|
||
x = self.lrelu(x)
|
||
x = torch.transpose(x, 1, -1) # [b, h, t]
|
||
x_mask = torch.unsqueeze(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 TextEncoder768(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(768, hidden_channels)
|
||
self.lrelu = nn.LeakyReLU(0.1, inplace=True)
|
||
if f0 == True:
|
||
self.emb_pitch = nn.Embedding(256, hidden_channels) # pitch 256
|
||
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 is None:
|
||
x = self.emb_phone(phone)
|
||
else:
|
||
x = self.emb_phone(phone) + self.emb_pitch(pitch)
|
||
x = x * math.sqrt(self.hidden_channels) # [b, t, h]
|
||
x = self.lrelu(x)
|
||
x = torch.transpose(x, 1, -1) # [b, h, t]
|
||
x_mask = torch.unsqueeze(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 TextEncoder(nn.Module):
|
||
def __init__(self,
|
||
n_vocab,
|
||
out_channels,
|
||
hidden_channels,
|
||
filter_channels,
|
||
n_heads,
|
||
n_layers,
|
||
kernel_size,
|
||
p_dropout):
|
||
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.emb = nn.Embedding(n_vocab, hidden_channels)
|
||
nn.init.normal_(self.emb.weight, 0.0, hidden_channels**-0.5)
|
||
|
||
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, x, x_lengths):
|
||
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(sequence_mask(x_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 x, 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(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 SineGen(torch.nn.Module):
|
||
"""Definition of sine generator
|
||
SineGen(samp_rate, harmonic_num = 0,
|
||
sine_amp = 0.1, noise_std = 0.003,
|
||
voiced_threshold = 0,
|
||
flag_for_pulse=False)
|
||
samp_rate: sampling rate in Hz
|
||
harmonic_num: number of harmonic overtones (default 0)
|
||
sine_amp: amplitude of sine-wavefrom (default 0.1)
|
||
noise_std: std of Gaussian noise (default 0.003)
|
||
voiced_thoreshold: F0 threshold for U/V classification (default 0)
|
||
flag_for_pulse: this SinGen is used inside PulseGen (default False)
|
||
Note: when flag_for_pulse is True, the first time step of a voiced
|
||
segment is always sin(np.pi) or cos(0)
|
||
"""
|
||
|
||
def __init__(
|
||
self,
|
||
samp_rate,
|
||
harmonic_num=0,
|
||
sine_amp=0.1,
|
||
noise_std=0.003,
|
||
voiced_threshold=0,
|
||
flag_for_pulse=False,
|
||
):
|
||
super(SineGen, self).__init__()
|
||
self.sine_amp = sine_amp
|
||
self.noise_std = noise_std
|
||
self.harmonic_num = harmonic_num
|
||
self.dim = self.harmonic_num + 1
|
||
self.sampling_rate = samp_rate
|
||
self.voiced_threshold = voiced_threshold
|
||
|
||
def _f02uv(self, f0):
|
||
# generate uv signal
|
||
uv = torch.ones_like(f0)
|
||
uv = uv * (f0 > self.voiced_threshold)
|
||
if uv.device.type == "privateuseone": # for DirectML
|
||
uv = uv.float()
|
||
return uv
|
||
|
||
def forward(self, f0, upp):
|
||
"""sine_tensor, uv = forward(f0)
|
||
input F0: tensor(batchsize=1, length, dim=1)
|
||
f0 for unvoiced steps should be 0
|
||
output sine_tensor: tensor(batchsize=1, length, dim)
|
||
output uv: tensor(batchsize=1, length, 1)
|
||
"""
|
||
with torch.no_grad():
|
||
f0 = f0[:, None].transpose(1, 2)
|
||
f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
|
||
# fundamental component
|
||
f0_buf[:, :, 0] = f0[:, :, 0]
|
||
for idx in np.arange(self.harmonic_num):
|
||
f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (
|
||
idx + 2
|
||
) # idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic
|
||
rad_values = (f0_buf / self.sampling_rate) % 1 ###%1意味着n_har的乘积无法后处理优化
|
||
rand_ini = torch.rand(
|
||
f0_buf.shape[0], f0_buf.shape[2], device=f0_buf.device
|
||
)
|
||
rand_ini[:, 0] = 0
|
||
rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
|
||
tmp_over_one = torch.cumsum(rad_values, 1) # % 1 #####%1意味着后面的cumsum无法再优化
|
||
tmp_over_one *= upp
|
||
tmp_over_one = F.interpolate(
|
||
tmp_over_one.transpose(2, 1),
|
||
scale_factor=upp,
|
||
mode="linear",
|
||
align_corners=True,
|
||
).transpose(2, 1)
|
||
rad_values = F.interpolate(
|
||
rad_values.transpose(2, 1), scale_factor=upp, mode="nearest"
|
||
).transpose(
|
||
2, 1
|
||
) #######
|
||
tmp_over_one %= 1
|
||
tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0
|
||
cumsum_shift = torch.zeros_like(rad_values)
|
||
cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
|
||
sine_waves = torch.sin(
|
||
torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * np.pi
|
||
)
|
||
sine_waves = sine_waves * self.sine_amp
|
||
uv = self._f02uv(f0)
|
||
uv = F.interpolate(
|
||
uv.transpose(2, 1), scale_factor=upp, mode="nearest"
|
||
).transpose(2, 1)
|
||
noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
|
||
noise = noise_amp * torch.randn_like(sine_waves)
|
||
sine_waves = sine_waves * uv + noise
|
||
return sine_waves, uv, noise
|
||
|
||
|
||
class SourceModuleHnNSF(torch.nn.Module):
|
||
"""SourceModule for hn-nsf
|
||
SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
|
||
add_noise_std=0.003, voiced_threshod=0)
|
||
sampling_rate: sampling_rate in Hz
|
||
harmonic_num: number of harmonic above F0 (default: 0)
|
||
sine_amp: amplitude of sine source signal (default: 0.1)
|
||
add_noise_std: std of additive Gaussian noise (default: 0.003)
|
||
note that amplitude of noise in unvoiced is decided
|
||
by sine_amp
|
||
voiced_threshold: threhold to set U/V given F0 (default: 0)
|
||
Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
|
||
F0_sampled (batchsize, length, 1)
|
||
Sine_source (batchsize, length, 1)
|
||
noise_source (batchsize, length 1)
|
||
uv (batchsize, length, 1)
|
||
"""
|
||
|
||
def __init__(
|
||
self,
|
||
sampling_rate,
|
||
harmonic_num=0,
|
||
sine_amp=0.1,
|
||
add_noise_std=0.003,
|
||
voiced_threshod=0,
|
||
is_half=True,
|
||
):
|
||
super(SourceModuleHnNSF, self).__init__()
|
||
|
||
self.sine_amp = sine_amp
|
||
self.noise_std = add_noise_std
|
||
self.is_half = is_half
|
||
# to produce sine waveforms
|
||
self.l_sin_gen = SineGen(
|
||
sampling_rate, harmonic_num, sine_amp, add_noise_std, voiced_threshod
|
||
)
|
||
|
||
# to merge source harmonics into a single excitation
|
||
self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
|
||
self.l_tanh = torch.nn.Tanh()
|
||
|
||
def forward(self, x, upp=None):
|
||
if hasattr(self, "ddtype") == False:
|
||
self.ddtype = self.l_linear.weight.dtype
|
||
sine_wavs, uv, _ = self.l_sin_gen(x, upp)
|
||
# print(x.dtype,sine_wavs.dtype,self.l_linear.weight.dtype)
|
||
# if self.is_half:
|
||
# sine_wavs = sine_wavs.half()
|
||
# sine_merge = self.l_tanh(self.l_linear(sine_wavs.to(x)))
|
||
# print(sine_wavs.dtype,self.ddtype)
|
||
if sine_wavs.dtype != self.ddtype:
|
||
sine_wavs = sine_wavs.to(self.ddtype)
|
||
sine_merge = self.l_tanh(self.l_linear(sine_wavs))
|
||
return sine_merge, None, None # noise, uv
|
||
|
||
|
||
class GeneratorNSF(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,
|
||
sr,
|
||
is_half=False,
|
||
):
|
||
super(GeneratorNSF, self).__init__()
|
||
self.num_kernels = len(resblock_kernel_sizes)
|
||
self.num_upsamples = len(upsample_rates)
|
||
|
||
self.f0_upsamp = torch.nn.Upsample(scale_factor=np.prod(upsample_rates))
|
||
self.m_source = SourceModuleHnNSF(
|
||
sampling_rate=sr, harmonic_num=0, is_half=is_half
|
||
)
|
||
self.noise_convs = nn.ModuleList()
|
||
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)):
|
||
c_cur = upsample_initial_channel // (2 ** (i + 1))
|
||
self.ups.append(
|
||
weight_norm(
|
||
ConvTranspose1d(
|
||
upsample_initial_channel // (2**i),
|
||
upsample_initial_channel // (2 ** (i + 1)),
|
||
k,
|
||
u,
|
||
padding=(k - u) // 2,
|
||
)
|
||
)
|
||
)
|
||
if i + 1 < len(upsample_rates):
|
||
stride_f0 = np.prod(upsample_rates[i + 1 :])
|
||
self.noise_convs.append(
|
||
Conv1d(
|
||
1,
|
||
c_cur,
|
||
kernel_size=stride_f0 * 2,
|
||
stride=stride_f0,
|
||
padding=stride_f0 // 2,
|
||
)
|
||
)
|
||
else:
|
||
self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))
|
||
|
||
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)
|
||
|
||
self.upp = np.prod(upsample_rates)
|
||
|
||
def forward(self, x, f0, g=None):
|
||
har_source, noi_source, uv = self.m_source(f0, self.upp)
|
||
har_source = har_source.transpose(1, 2)
|
||
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)
|
||
x_source = self.noise_convs[i](har_source)
|
||
x = x + x_source
|
||
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()
|
||
|
||
|
||
sr2sr = {
|
||
"32k": 32000,
|
||
"40k": 40000,
|
||
"48k": 48000,
|
||
}
|
||
|
||
|
||
class SynthesizerTrnMs256NSFsid(nn.Module):
|
||
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,
|
||
spk_embed_dim,
|
||
gin_channels,
|
||
sr,
|
||
**kwargs
|
||
):
|
||
super().__init__()
|
||
if type(sr) == type("strr"):
|
||
sr = sr2sr[sr]
|
||
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.hop_length = hop_length#
|
||
self.spk_embed_dim = spk_embed_dim
|
||
self.enc_p = TextEncoder256(
|
||
inter_channels,
|
||
hidden_channels,
|
||
filter_channels,
|
||
n_heads,
|
||
n_layers,
|
||
kernel_size,
|
||
p_dropout,
|
||
)
|
||
self.dec = GeneratorNSF(
|
||
inter_channels,
|
||
resblock,
|
||
resblock_kernel_sizes,
|
||
resblock_dilation_sizes,
|
||
upsample_rates,
|
||
upsample_initial_channel,
|
||
upsample_kernel_sizes,
|
||
gin_channels=gin_channels,
|
||
sr=sr,
|
||
is_half=kwargs["is_half"],
|
||
)
|
||
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
|
||
)
|
||
self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
|
||
|
||
|
||
def remove_weight_norm(self):
|
||
self.dec.remove_weight_norm()
|
||
self.flow.remove_weight_norm()
|
||
self.enc_q.remove_weight_norm()
|
||
|
||
def forward(
|
||
self, phone, phone_lengths, pitch, pitchf, y, y_lengths, ds
|
||
): # 这里ds是id，[bs,1]
|
||
# print(1,pitch.shape)#[bs,t]
|
||
g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
|
||
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
|
||
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
|
||
z_p = self.flow(z, y_mask, g=g)
|
||
z_slice, ids_slice = rand_slice_segments(
|
||
z, y_lengths, self.segment_size
|
||
)
|
||
# print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
|
||
pitchf = slice_segments2(pitchf, ids_slice, self.segment_size)
|
||
# print(-2,pitchf.shape,z_slice.shape)
|
||
o = self.dec(z_slice, pitchf, g=g)
|
||
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
|
||
|
||
def infer(self, phone, phone_lengths, pitch, nsff0, sid, rate=None):
|
||
g = self.emb_g(sid).unsqueeze(-1)
|
||
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
|
||
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
|
||
if rate:
|
||
head = int(z_p.shape[2] * rate)
|
||
z_p = z_p[:, :, -head:]
|
||
x_mask = x_mask[:, :, -head:]
|
||
nsff0 = nsff0[:, -head:]
|
||
z = self.flow(z_p, x_mask, g=g, reverse=True)
|
||
o = self.dec(z * x_mask, nsff0, g=g)
|
||
return o, x_mask, (z, z_p, m_p, logs_p)
|
||
|
||
|
||
class SynthesizerTrnMs768NSFsid(nn.Module):
|
||
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,
|
||
spk_embed_dim,
|
||
gin_channels,
|
||
sr,
|
||
**kwargs
|
||
):
|
||
super().__init__()
|
||
if type(sr) == type("strr"):
|
||
sr = sr2sr[sr]
|
||
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.hop_length = hop_length#
|
||
self.spk_embed_dim = spk_embed_dim
|
||
self.enc_p = TextEncoder768(
|
||
inter_channels,
|
||
hidden_channels,
|
||
filter_channels,
|
||
n_heads,
|
||
n_layers,
|
||
kernel_size,
|
||
p_dropout,
|
||
)
|
||
self.dec = GeneratorNSF(
|
||
inter_channels,
|
||
resblock,
|
||
resblock_kernel_sizes,
|
||
resblock_dilation_sizes,
|
||
upsample_rates,
|
||
upsample_initial_channel,
|
||
upsample_kernel_sizes,
|
||
gin_channels=gin_channels,
|
||
sr=sr,
|
||
is_half=kwargs["is_half"],
|
||
)
|
||
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
|
||
)
|
||
self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
|
||
|
||
|
||
def remove_weight_norm(self):
|
||
self.dec.remove_weight_norm()
|
||
self.flow.remove_weight_norm()
|
||
self.enc_q.remove_weight_norm()
|
||
|
||
def forward(
|
||
self, phone, phone_lengths, pitch, pitchf, y, y_lengths, ds
|
||
): # 这里ds是id，[bs,1]
|
||
# print(1,pitch.shape)#[bs,t]
|
||
g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
|
||
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
|
||
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
|
||
z_p = self.flow(z, y_mask, g=g)
|
||
z_slice, ids_slice = rand_slice_segments(
|
||
z, y_lengths, self.segment_size
|
||
)
|
||
# print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
|
||
pitchf = slice_segments2(pitchf, ids_slice, self.segment_size)
|
||
# print(-2,pitchf.shape,z_slice.shape)
|
||
o = self.dec(z_slice, pitchf, g=g)
|
||
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
|
||
|
||
def infer(self, phone, phone_lengths, pitch, nsff0, sid, rate=None):
|
||
g = self.emb_g(sid).unsqueeze(-1)
|
||
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
|
||
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
|
||
if rate:
|
||
head = int(z_p.shape[2] * rate)
|
||
z_p = z_p[:, :, -head:]
|
||
x_mask = x_mask[:, :, -head:]
|
||
nsff0 = nsff0[:, -head:]
|
||
z = self.flow(z_p, x_mask, g=g, reverse=True)
|
||
o = self.dec(z * x_mask, nsff0, g=g)
|
||
return o, x_mask, (z, z_p, m_p, logs_p)
|
||
|
||
|
||
class SynthesizerTrnMs256NSFsid_nono(nn.Module):
|
||
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,
|
||
spk_embed_dim,
|
||
gin_channels,
|
||
sr=None,
|
||
**kwargs
|
||
):
|
||
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.hop_length = hop_length#
|
||
self.spk_embed_dim = spk_embed_dim
|
||
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
|
||
)
|
||
self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
|
||
|
||
|
||
def remove_weight_norm(self):
|
||
self.dec.remove_weight_norm()
|
||
self.flow.remove_weight_norm()
|
||
self.enc_q.remove_weight_norm()
|
||
|
||
def forward(self, phone, phone_lengths, y, y_lengths, ds): # 这里ds是id，[bs,1]
|
||
g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
|
||
m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
|
||
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
|
||
z_p = self.flow(z, y_mask, g=g)
|
||
z_slice, ids_slice = rand_slice_segments(
|
||
z, y_lengths, self.segment_size
|
||
)
|
||
o = self.dec(z_slice, g=g)
|
||
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
|
||
|
||
def infer(self, phone, phone_lengths, sid, rate=None):
|
||
g = self.emb_g(sid).unsqueeze(-1)
|
||
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) * 0.66666) * x_mask
|
||
if rate:
|
||
head = int(z_p.shape[2] * rate)
|
||
z_p = z_p[:, :, -head:]
|
||
x_mask = x_mask[:, :, -head:]
|
||
z = self.flow(z_p, x_mask, g=g, reverse=True)
|
||
o = self.dec(z * x_mask, g=g)
|
||
return o, x_mask, (z, z_p, m_p, logs_p)
|
||
|
||
|
||
class SynthesizerTrnMs768NSFsid_nono(nn.Module):
|
||
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,
|
||
spk_embed_dim,
|
||
gin_channels,
|
||
sr=None,
|
||
**kwargs
|
||
):
|
||
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.hop_length = hop_length#
|
||
self.spk_embed_dim = spk_embed_dim
|
||
self.enc_p = TextEncoder768(
|
||
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
|
||
)
|
||
self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
|
||
|
||
|
||
def remove_weight_norm(self):
|
||
self.dec.remove_weight_norm()
|
||
self.flow.remove_weight_norm()
|
||
self.enc_q.remove_weight_norm()
|
||
|
||
def forward(self, phone, phone_lengths, y, y_lengths, ds): # 这里ds是id，[bs,1]
|
||
g = self.emb_g(ds).unsqueeze(-1) # [b, 256, 1]##1是t，广播的
|
||
m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
|
||
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
|
||
z_p = self.flow(z, y_mask, g=g)
|
||
z_slice, ids_slice = rand_slice_segments(
|
||
z, y_lengths, self.segment_size
|
||
)
|
||
o = self.dec(z_slice, g=g)
|
||
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
|
||
|
||
def infer(self, phone, phone_lengths, sid, rate=None):
|
||
g = self.emb_g(sid).unsqueeze(-1)
|
||
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) * 0.66666) * x_mask
|
||
if rate:
|
||
head = int(z_p.shape[2] * rate)
|
||
z_p = z_p[:, :, -head:]
|
||
x_mask = x_mask[:, :, -head:]
|
||
z = self.flow(z_p, x_mask, g=g, reverse=True)
|
||
o = self.dec(z * x_mask, g=g)
|
||
return o, x_mask, (z, z_p, m_p, logs_p)
|
||
|
||
|
||
class MultiPeriodDiscriminator(torch.nn.Module):
|
||
def __init__(self, use_spectral_norm=False):
|
||
super(MultiPeriodDiscriminator, self).__init__()
|
||
periods = [2, 3, 5, 7, 11, 17]
|
||
# periods = [3, 5, 7, 11, 17, 23, 37]
|
||
|
||
discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
|
||
discs = discs + [
|
||
DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
|
||
]
|
||
self.discriminators = nn.ModuleList(discs)
|
||
|
||
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)
|
||
y_d_gs.append(y_d_g)
|
||
fmap_rs.append(fmap_r)
|
||
fmap_gs.append(fmap_g)
|
||
|
||
return y_d_rs, y_d_gs, fmap_rs, fmap_gs
|
||
|
||
|
||
class MultiPeriodDiscriminatorV2(torch.nn.Module):
|
||
def __init__(self, use_spectral_norm=False):
|
||
super(MultiPeriodDiscriminatorV2, self).__init__()
|
||
# periods = [2, 3, 5, 7, 11, 17]
|
||
periods = [2, 3, 5, 7, 11, 17, 23, 37]
|
||
|
||
discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
|
||
discs = discs + [
|
||
DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
|
||
]
|
||
self.discriminators = nn.ModuleList(discs)
|
||
|
||
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)
|
||
# for j in range(len(fmap_r)):
|
||
# print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
|
||
y_d_rs.append(y_d_r)
|
||
y_d_gs.append(y_d_g)
|
||
fmap_rs.append(fmap_r)
|
||
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, 16, 15, 1, padding=7)),
|
||
norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
|
||
norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
|
||
norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
|
||
norm_f(Conv1d(1024, 1024, 41, 4, groups=256, 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, modules.LRELU_SLOPE)
|
||
fmap.append(x)
|
||
x = self.conv_post(x)
|
||
fmap.append(x)
|
||
x = torch.flatten(x, 1, -1)
|
||
|
||
return x, fmap
|
||
|
||
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
|
||
self.use_spectral_norm = use_spectral_norm
|
||
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(kernel_size, 1), 0))),
|
||
norm_f(Conv2d(32, 128, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
|
||
norm_f(Conv2d(128, 512, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
|
||
norm_f(Conv2d(512, 1024, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
|
||
norm_f(Conv2d(1024, 1024, (kernel_size, 1), 1, padding=(get_padding(kernel_size, 1), 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, modules.LRELU_SLOPE)
|
||
fmap.append(x)
|
||
x = self.conv_post(x)
|
||
fmap.append(x)
|
||
x = torch.flatten(x, 1, -1)
|
||
|
||
return x, fmap
|
||
|
||
class StochasticDurationPredictor(nn.Module):
|
||
def __init__(self, in_channels, filter_channels, kernel_size, p_dropout, n_flows=4, gin_channels=0):
|
||
super().__init__()
|
||
filter_channels = in_channels # it needs to be removed from future version.
|
||
self.in_channels = in_channels
|
||
self.filter_channels = filter_channels
|
||
self.kernel_size = kernel_size
|
||
self.p_dropout = p_dropout
|
||
self.n_flows = n_flows
|
||
self.gin_channels = gin_channels
|
||
|
||
self.log_flow = modules.Log()
|
||
self.flows = nn.ModuleList()
|
||
self.flows.append(modules.ElementwiseAffine(2))
|
||
for i in range(n_flows):
|
||
self.flows.append(modules.ConvFlow(2, filter_channels, kernel_size, n_layers=3))
|
||
self.flows.append(modules.Flip())
|
||
|
||
self.post_pre = nn.Conv1d(1, filter_channels, 1)
|
||
self.post_proj = nn.Conv1d(filter_channels, filter_channels, 1)
|
||
self.post_convs = modules.DDSConv(filter_channels, kernel_size, n_layers=3, p_dropout=p_dropout)
|
||
self.post_flows = nn.ModuleList()
|
||
self.post_flows.append(modules.ElementwiseAffine(2))
|
||
for i in range(4):
|
||
self.post_flows.append(modules.ConvFlow(2, filter_channels, kernel_size, n_layers=3))
|
||
self.post_flows.append(modules.Flip())
|
||
|
||
self.pre = nn.Conv1d(in_channels, filter_channels, 1)
|
||
self.proj = nn.Conv1d(filter_channels, filter_channels, 1)
|
||
self.convs = modules.DDSConv(filter_channels, kernel_size, n_layers=3, p_dropout=p_dropout)
|
||
if gin_channels != 0:
|
||
self.cond = nn.Conv1d(gin_channels, filter_channels, 1)
|
||
|
||
def forward(self, x, x_mask, w=None, g=None, reverse=False, noise_scale=1.0):
|
||
x = torch.detach(x)
|
||
x = self.pre(x)
|
||
if g is not None:
|
||
g = torch.detach(g)
|
||
x = x + self.cond(g)
|
||
x = self.convs(x, x_mask)
|
||
x = self.proj(x) * x_mask
|
||
|
||
if not reverse:
|
||
flows = self.flows
|
||
assert w is not None
|
||
|
||
logdet_tot_q = 0
|
||
h_w = self.post_pre(w)
|
||
h_w = self.post_convs(h_w, x_mask)
|
||
h_w = self.post_proj(h_w) * x_mask
|
||
e_q = torch.randn(w.size(0), 2, w.size(2)).to(device=x.device, dtype=x.dtype) * x_mask
|
||
z_q = e_q
|
||
for flow in self.post_flows:
|
||
z_q, logdet_q = flow(z_q, x_mask, g=(x + h_w))
|
||
logdet_tot_q += logdet_q
|
||
z_u, z1 = torch.split(z_q, [1, 1], 1)
|
||
u = torch.sigmoid(z_u) * x_mask
|
||
z0 = (w - u) * x_mask
|
||
logdet_tot_q += torch.sum((F.logsigmoid(z_u) + F.logsigmoid(-z_u)) * x_mask, [1,2])
|
||
logq = torch.sum(-0.5 * (math.log(2*math.pi) + (e_q**2)) * x_mask, [1,2]) - logdet_tot_q
|
||
|
||
logdet_tot = 0
|
||
z0, logdet = self.log_flow(z0, x_mask)
|
||
logdet_tot += logdet
|
||
z = torch.cat([z0, z1], 1)
|
||
for flow in flows:
|
||
z, logdet = flow(z, x_mask, g=x, reverse=reverse)
|
||
logdet_tot = logdet_tot + logdet
|
||
nll = torch.sum(0.5 * (math.log(2*math.pi) + (z**2)) * x_mask, [1,2]) - logdet_tot
|
||
return nll + logq # [b]
|
||
else:
|
||
flows = list(reversed(self.flows))
|
||
flows = flows[:-2] + [flows[-1]] # remove a useless vflow
|
||
z = torch.randn(x.size(0), 2, x.size(2)).to(device=x.device, dtype=x.dtype) * noise_scale
|
||
for flow in flows:
|
||
z = flow(z, x_mask, g=x, reverse=reverse)
|
||
z0, z1 = torch.split(z, [1, 1], 1)
|
||
logw = z0
|
||
return logw
|
||
|
||
class DurationPredictor(nn.Module):
|
||
def __init__(self, in_channels, filter_channels, kernel_size, p_dropout, gin_channels=0):
|
||
super().__init__()
|
||
|
||
self.in_channels = in_channels
|
||
self.filter_channels = filter_channels
|
||
self.kernel_size = kernel_size
|
||
self.p_dropout = p_dropout
|
||
self.gin_channels = gin_channels
|
||
|
||
self.drop = nn.Dropout(p_dropout)
|
||
self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size, padding=kernel_size//2)
|
||
self.norm_1 = modules.LayerNorm(filter_channels)
|
||
self.conv_2 = nn.Conv1d(filter_channels, filter_channels, kernel_size, padding=kernel_size//2)
|
||
self.norm_2 = modules.LayerNorm(filter_channels)
|
||
self.proj = nn.Conv1d(filter_channels, 1, 1)
|
||
|
||
if gin_channels != 0:
|
||
self.cond = nn.Conv1d(gin_channels, in_channels, 1)
|
||
|
||
def forward(self, x, x_mask, g=None):
|
||
x = torch.detach(x)
|
||
if g is not None:
|
||
g = torch.detach(g)
|
||
x = x + self.cond(g)
|
||
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
|
||
|
||
class SynthesizerTrn(nn.Module):
|
||
"""
|
||
Synthesizer for Training
|
||
"""
|
||
|
||
def __init__(self,
|
||
n_vocab,
|
||
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,
|
||
n_speakers=0,
|
||
gin_channels=0,
|
||
use_sdp=True,
|
||
**kwargs):
|
||
|
||
super().__init__()
|
||
self.n_vocab = n_vocab
|
||
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.n_speakers = n_speakers
|
||
self.gin_channels = gin_channels
|
||
|
||
self.use_sdp = use_sdp
|
||
|
||
self.enc_p = TextEncoder(n_vocab,
|
||
inter_channels,
|
||
hidden_channels,
|
||
filter_channels,
|
||
n_heads,
|
||
n_layers,
|
||
kernel_size,
|
||
p_dropout)
|
||
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, 4, gin_channels=gin_channels)
|
||
|
||
if use_sdp:
|
||
self.dp = StochasticDurationPredictor(hidden_channels, 192, 3, 0.5, 4, gin_channels=gin_channels)
|
||
else:
|
||
self.dp = DurationPredictor(hidden_channels, 256, 3, 0.5, gin_channels=gin_channels)
|
||
|
||
if n_speakers > 1:
|
||
self.emb_g = nn.Embedding(n_speakers, gin_channels)
|
||
|
||
def forward(self, x, x_lengths, y, y_lengths, sid=None):
|
||
|
||
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths)
|
||
if self.n_speakers > 0:
|
||
g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1]
|
||
else:
|
||
g = None
|
||
|
||
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
|
||
z_p = self.flow(z, y_mask, g=g)
|
||
|
||
with torch.no_grad():
|
||
# negative cross-entropy
|
||
s_p_sq_r = torch.exp(-2 * logs_p) # [b, d, t]
|
||
neg_cent1 = torch.sum(-0.5 * math.log(2 * math.pi) - logs_p, [1], keepdim=True) # [b, 1, t_s]
|
||
neg_cent2 = torch.matmul(-0.5 * (z_p ** 2).transpose(1, 2), s_p_sq_r) # [b, t_t, d] x [b, d, t_s] = [b, t_t, t_s]
|
||
neg_cent3 = torch.matmul(z_p.transpose(1, 2), (m_p * s_p_sq_r)) # [b, t_t, d] x [b, d, t_s] = [b, t_t, t_s]
|
||
neg_cent4 = torch.sum(-0.5 * (m_p ** 2) * s_p_sq_r, [1], keepdim=True) # [b, 1, t_s]
|
||
neg_cent = neg_cent1 + neg_cent2 + neg_cent3 + neg_cent4
|
||
|
||
attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
|
||
attn = monotonic_align.maximum_path(neg_cent, attn_mask.squeeze(1)).unsqueeze(1).detach()
|
||
|
||
w = attn.sum(2)
|
||
if self.use_sdp:
|
||
l_length = self.dp(x, x_mask, w, g=g)
|
||
l_length = l_length / torch.sum(x_mask)
|
||
else:
|
||
logw_ = torch.log(w + 1e-6) * x_mask
|
||
logw = self.dp(x, x_mask, g=g)
|
||
l_length = torch.sum((logw - logw_)**2, [1,2]) / torch.sum(x_mask) # for averaging
|
||
|
||
# expand prior
|
||
m_p = torch.matmul(attn.squeeze(1), m_p.transpose(1, 2)).transpose(1, 2)
|
||
logs_p = torch.matmul(attn.squeeze(1), logs_p.transpose(1, 2)).transpose(1, 2)
|
||
|
||
z_slice, ids_slice = rand_slice_segments(z, y_lengths, self.segment_size)
|
||
o = self.dec(z_slice, g=g)
|
||
return o, l_length, attn, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
|
||
|
||
def infer(self, x, x_lengths, sid=None, noise_scale=1, length_scale=1, noise_scale_w=1., max_len=None):
|
||
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths)
|
||
if self.n_speakers > 0:
|
||
g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1]
|
||
else:
|
||
g = None
|
||
|
||
if self.use_sdp:
|
||
logw = self.dp(x, x_mask, g=g, reverse=True, noise_scale=noise_scale_w)
|
||
else:
|
||
logw = self.dp(x, x_mask, g=g)
|
||
w = torch.exp(logw) * x_mask * length_scale
|
||
w_ceil = torch.ceil(w)
|
||
y_lengths = torch.clamp_min(torch.sum(w_ceil, [1, 2]), 1).long()
|
||
y_mask = torch.unsqueeze(sequence_mask(y_lengths, None), 1).to(x_mask.dtype)
|
||
attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
|
||
attn = generate_path(w_ceil, attn_mask)
|
||
|
||
m_p = torch.matmul(attn.squeeze(1), m_p.transpose(1, 2)).transpose(1, 2) # [b, t', t], [b, t, d] -> [b, d, t']
|
||
logs_p = torch.matmul(attn.squeeze(1), logs_p.transpose(1, 2)).transpose(1, 2) # [b, t', t], [b, t, d] -> [b, d, t']
|
||
|
||
z_p = m_p + torch.randn_like(m_p) * torch.exp(logs_p) * noise_scale
|
||
z = self.flow(z_p, y_mask, g=g, reverse=True)
|
||
o = self.dec((z * y_mask)[:,:,:max_len], g=g)
|
||
return o, attn, y_mask, (z, z_p, m_p, logs_p)
|
||
|
||
def voice_conversion(self, y, y_lengths, sid_src, sid_tgt):
|
||
assert self.n_speakers > 0, "n_speakers have to be larger than 0."
|
||
g_src = self.emb_g(sid_src).unsqueeze(-1)
|
||
g_tgt = self.emb_g(sid_tgt).unsqueeze(-1)
|
||
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g_src)
|
||
z_p = self.flow(z, y_mask, g=g_src)
|
||
z_hat = self.flow(z_p, y_mask, g=g_tgt, reverse=True)
|
||
o_hat = self.dec(z_hat * y_mask, g=g_tgt)
|
||
return o_hat, y_mask, (z, z_p, z_hat) |