upload files
This commit is contained in:
Plachta
@@ -1,3 +1,4 @@
|
||||
import copy
|
||||
import math
|
||||
import torch
|
||||
from torch import nn
|
||||
@@ -8,251 +9,240 @@ import modules
|
||||
import attentions
|
||||
import monotonic_align
|
||||
|
||||
from torch.nn import Conv1d, ConvTranspose1d, Conv2d
|
||||
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, get_padding
|
||||
|
||||
|
||||
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
|
||||
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.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.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)
|
||||
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
|
||||
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
|
||||
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_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
|
||||
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__()
|
||||
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.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)
|
||||
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)
|
||||
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
|
||||
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 TextEncoder(nn.Module):
|
||||
def __init__(self,
|
||||
n_vocab,
|
||||
out_channels,
|
||||
hidden_channels,
|
||||
filter_channels,
|
||||
n_heads,
|
||||
n_layers,
|
||||
kernel_size,
|
||||
p_dropout,
|
||||
emotion_embedding):
|
||||
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.emotion_embedding = emotion_embedding
|
||||
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
|
||||
|
||||
if self.n_vocab != 0:
|
||||
self.emb = nn.Embedding(n_vocab, hidden_channels)
|
||||
if emotion_embedding:
|
||||
self.emo_proj = nn.Linear(1024, hidden_channels)
|
||||
nn.init.normal_(self.emb.weight, 0.0, hidden_channels ** -0.5)
|
||||
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)
|
||||
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, emotion_embedding=None):
|
||||
if self.n_vocab != 0:
|
||||
x = self.emb(x) * math.sqrt(self.hidden_channels) # [b, t, h]
|
||||
if emotion_embedding is not None:
|
||||
x = x + self.emo_proj(emotion_embedding.unsqueeze(1))
|
||||
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)
|
||||
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(commons.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
|
||||
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
|
||||
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
|
||||
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())
|
||||
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 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
|
||||
|
||||
|
||||
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
|
||||
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)
|
||||
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 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
|
||||
|
||||
|
||||
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):
|
||||
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)
|
||||
@@ -262,12 +252,12 @@ class Generator(torch.nn.Module):
|
||||
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)))
|
||||
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))
|
||||
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))
|
||||
|
||||
@@ -280,7 +270,7 @@ class Generator(torch.nn.Module):
|
||||
def forward(self, x, g=None):
|
||||
x = self.conv_pre(x)
|
||||
if g is not None:
|
||||
x = x + self.cond(g)
|
||||
x = x + self.cond(g)
|
||||
|
||||
for i in range(self.num_upsamples):
|
||||
x = F.leaky_relu(x, modules.LRELU_SLOPE)
|
||||
@@ -288,9 +278,9 @@ class Generator(torch.nn.Module):
|
||||
xs = None
|
||||
for j in range(self.num_kernels):
|
||||
if xs is None:
|
||||
xs = self.resblocks[i * self.num_kernels + j](x)
|
||||
xs = self.resblocks[i*self.num_kernels+j](x)
|
||||
else:
|
||||
xs += self.resblocks[i * self.num_kernels + j](x)
|
||||
xs += self.resblocks[i*self.num_kernels+j](x)
|
||||
x = xs / self.num_kernels
|
||||
x = F.leaky_relu(x)
|
||||
x = self.conv_post(x)
|
||||
@@ -326,7 +316,7 @@ class DiscriminatorP(torch.nn.Module):
|
||||
|
||||
# 1d to 2d
|
||||
b, c, t = x.shape
|
||||
if t % self.period != 0: # pad first
|
||||
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
|
||||
@@ -374,7 +364,7 @@ class DiscriminatorS(torch.nn.Module):
|
||||
class MultiPeriodDiscriminator(torch.nn.Module):
|
||||
def __init__(self, use_spectral_norm=False):
|
||||
super(MultiPeriodDiscriminator, self).__init__()
|
||||
periods = [2, 3, 5, 7, 11]
|
||||
periods = [2,3,5,7,11]
|
||||
|
||||
discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
|
||||
discs = discs + [DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods]
|
||||
@@ -396,195 +386,148 @@ class MultiPeriodDiscriminator(torch.nn.Module):
|
||||
return y_d_rs, y_d_gs, fmap_rs, fmap_gs
|
||||
|
||||
|
||||
|
||||
class SynthesizerTrn(nn.Module):
|
||||
"""
|
||||
Synthesizer for Training
|
||||
"""
|
||||
"""
|
||||
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,
|
||||
emotion_embedding=False,
|
||||
**kwargs):
|
||||
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
|
||||
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.use_sdp = use_sdp
|
||||
|
||||
self.enc_p = TextEncoder(n_vocab,
|
||||
inter_channels,
|
||||
hidden_channels,
|
||||
filter_channels,
|
||||
n_heads,
|
||||
n_layers,
|
||||
kernel_size,
|
||||
p_dropout,
|
||||
emotion_embedding)
|
||||
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)
|
||||
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 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)
|
||||
if n_speakers > 1:
|
||||
self.emb_g = nn.Embedding(n_speakers, gin_channels)
|
||||
|
||||
def forward(self, x, x_lengths, y, y_lengths, sid=None, emotion_embedding=None):
|
||||
def forward(self, x, x_lengths, y, y_lengths, sid=None):
|
||||
|
||||
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, emotion_embedding)
|
||||
if self.n_speakers > 1:
|
||||
g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1]
|
||||
else:
|
||||
g = 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)
|
||||
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
|
||||
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()
|
||||
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
|
||||
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)
|
||||
# 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 = commons.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)
|
||||
z_slice, ids_slice = commons.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,
|
||||
emotion_embedding=None):
|
||||
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, emotion_embedding)
|
||||
if self.n_speakers > 1:
|
||||
g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1]
|
||||
else:
|
||||
g = None
|
||||
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(commons.sequence_mask(y_lengths, None), 1).to(x_mask.dtype)
|
||||
attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
|
||||
attn = commons.generate_path(w_ceil, attn_mask)
|
||||
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(commons.sequence_mask(y_lengths, None), 1).to(x_mask.dtype)
|
||||
attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
|
||||
attn = commons.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']
|
||||
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)
|
||||
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 predict_duration(self, x, x_lengths, sid=None, noise_scale=1, length_scale=1, noise_scale_w=1., max_len=None,
|
||||
emotion_embedding=None):
|
||||
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, emotion_embedding)
|
||||
if self.n_speakers > 1:
|
||||
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)
|
||||
return list(w_ceil.squeeze())
|
||||
|
||||
def infer_with_duration(self, x, x_lengths, w_ceil, sid=None, noise_scale=1, length_scale=1, noise_scale_w=1., max_len=None,
|
||||
emotion_embedding=None):
|
||||
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, emotion_embedding)
|
||||
if self.n_speakers > 1:
|
||||
g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1]
|
||||
else:
|
||||
g = None
|
||||
print(len(w_ceil))
|
||||
print(x.shape)
|
||||
assert len(w_ceil) == x.shape[2]
|
||||
w_ceil = torch.FloatTensor(w_ceil).reshape(1, 1, -1)
|
||||
y_lengths = torch.clamp_min(torch.sum(w_ceil, [1, 2]), 1).long()
|
||||
y_mask = torch.unsqueeze(commons.sequence_mask(y_lengths, None), 1).to(x_mask.dtype)
|
||||
attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
|
||||
attn = commons.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 > 1, "n_speakers have to be larger than 1."
|
||||
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)
|
||||
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)
|
||||
|
||||
Reference in New Issue
Block a user