File size: 12,160 Bytes
c968fc3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 |
# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
# This code is modified from https://github.com/jaywalnut310/vits/blob/main/models.py
import math
import torch
from torch import nn
from torch.nn import functional as F
from utils.util import *
from modules.flow.modules import *
from modules.base.base_module import *
from modules.transformer.attentions import Encoder
from modules.duration_predictor.standard_duration_predictor import DurationPredictor
from modules.duration_predictor.stochastic_duration_predictor import (
StochasticDurationPredictor,
)
from models.vocoders.gan.generator.hifigan import HiFiGAN_vits as Generator
try:
from modules import monotonic_align
except ImportError:
print("Monotonic align not found. Please make sure you have compiled it.")
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 = 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(
ResidualCouplingLayer(
channels,
hidden_channels,
kernel_size,
dilation_rate,
n_layers,
gin_channels=gin_channels,
mean_only=True,
)
)
self.flows.append(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
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 = 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
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, data):
x = data["phone_seq"]
x_lengths = data["phone_len"]
y = data["linear"]
y_lengths = data["target_len"]
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths)
if self.n_speakers > 0:
g = self.emb_g(data["spk_id"].squeeze(-1)).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)
# 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)
outputs = {
"y_hat": o,
"l_length": l_length,
"attn": attn,
"ids_slice": ids_slice,
"x_mask": x_mask,
"z_mask": y_mask,
"z": z,
"z_p": z_p,
"m_p": m_p,
"logs_p": logs_p,
"m_q": m_q,
"logs_q": logs_q,
}
return outputs
def infer(
self,
x,
x_lengths,
sid=None,
noise_scale=1,
length_scale=1,
noise_scale_w=1.0,
max_len=None,
):
x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths)
if self.n_speakers > 0:
sid = sid.squeeze(-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)
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)
outputs = {
"y_hat": o,
"attn": attn,
"mask": y_mask,
"z": z,
"z_p": z_p,
"m_p": m_p,
"logs_p": logs_p,
}
return outputs
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)
|