File size: 12,519 Bytes
c7b379a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 |
from typing import Optional, List, Union
import torch
from torch import nn
from .encoders import TextEncoder, PosteriorEncoder
from .generators import Generator
from .nsf import NSFGenerator
from .residuals import ResidualCouplingBlock
from .utils import (
slice_on_last_dim,
rand_slice_segments_on_last_dim,
)
class SynthesizerTrnMsNSFsid(nn.Module):
def __init__(
self,
spec_channels: int,
segment_size: int,
inter_channels: int,
hidden_channels: int,
filter_channels: int,
n_heads: int,
n_layers: int,
kernel_size: int,
p_dropout: int,
resblock: str,
resblock_kernel_sizes: List[int],
resblock_dilation_sizes: List[List[int]],
upsample_rates: List[int],
upsample_initial_channel: int,
upsample_kernel_sizes: List[int],
spk_embed_dim: int,
gin_channels: int,
sr: Optional[Union[str, int]],
encoder_dim: int,
use_f0: bool,
):
super().__init__()
if isinstance(sr, str):
sr = {
"32k": 32000,
"40k": 40000,
"48k": 48000,
}[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 = float(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.spk_embed_dim = spk_embed_dim
self.enc_p = TextEncoder(
encoder_dim,
inter_channels,
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
float(p_dropout),
f0=use_f0,
)
if use_f0:
self.dec = NSFGenerator(
inter_channels,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
gin_channels=gin_channels,
sr=sr,
)
else:
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()
if hasattr(self, "enc_q"):
self.enc_q.remove_weight_norm()
def __prepare_scriptable__(self):
for hook in self.dec._forward_pre_hooks.values():
# The hook we want to remove is an instance of WeightNorm class, so
# normally we would do `if isinstance(...)` but this class is not accessible
# because of shadowing, so we check the module name directly.
# https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(self.dec)
for hook in self.flow._forward_pre_hooks.values():
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(self.flow)
if hasattr(self, "enc_q"):
for hook in self.enc_q._forward_pre_hooks.values():
if (
hook.__module__ == "torch.nn.utils.weight_norm"
and hook.__class__.__name__ == "WeightNorm"
):
torch.nn.utils.remove_weight_norm(self.enc_q)
return self
@torch.jit.ignore
def forward(
self,
phone: torch.Tensor,
phone_lengths: torch.Tensor,
y: torch.Tensor,
y_lengths: torch.Tensor,
ds: Optional[torch.Tensor] = None,
pitch: Optional[torch.Tensor] = None,
pitchf: Optional[torch.Tensor] = None,
): # 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_on_last_dim(
z, y_lengths, self.segment_size
)
if pitchf is not None:
pitchf = slice_on_last_dim(pitchf, ids_slice, self.segment_size)
o = self.dec(z_slice, pitchf, g=g)
else:
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)
@torch.jit.export
def infer(
self,
phone: torch.Tensor,
phone_lengths: torch.Tensor,
sid: torch.Tensor,
pitch: Optional[torch.Tensor] = None,
pitchf: Optional[torch.Tensor] = None, # nsff0
skip_head: Optional[int] = None,
return_length: Optional[int] = None,
return_length2: Optional[int] = None,
):
g = self.emb_g(sid).unsqueeze(-1)
if skip_head is not None and return_length is not None:
head = int(skip_head)
length = int(return_length)
flow_head = head - 24
if flow_head < 0:
flow_head = 0
dec_head = head - flow_head
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths, flow_head)
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
z = self.flow(z_p, x_mask, g=g, reverse=True)
z = z[:, :, dec_head : dec_head + length]
x_mask = x_mask[:, :, dec_head : dec_head + length]
if pitchf is not None:
pitchf = pitchf[:, head : head + length]
else:
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
z = self.flow(z_p, x_mask, g=g, reverse=True)
del z_p, m_p, logs_p
if pitchf is not None:
o = self.dec(
z * x_mask,
pitchf,
g=g,
n_res=return_length2,
)
else:
o = self.dec(z * x_mask, g=g, n_res=return_length2)
del x_mask, z
return o # , x_mask, (z, z_p, m_p, logs_p)
class SynthesizerTrnMs256NSFsid(SynthesizerTrnMsNSFsid):
def __init__(
self,
spec_channels: int,
segment_size: int,
inter_channels: int,
hidden_channels: int,
filter_channels: int,
n_heads: int,
n_layers: int,
kernel_size: int,
p_dropout: int,
resblock: str,
resblock_kernel_sizes: List[int],
resblock_dilation_sizes: List[List[int]],
upsample_rates: List[int],
upsample_initial_channel: int,
upsample_kernel_sizes: List[int],
spk_embed_dim: int,
gin_channels: int,
sr: Union[str, int],
):
super().__init__(
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,
256,
True,
)
class SynthesizerTrnMs768NSFsid(SynthesizerTrnMsNSFsid):
def __init__(
self,
spec_channels: int,
segment_size: int,
inter_channels: int,
hidden_channels: int,
filter_channels: int,
n_heads: int,
n_layers: int,
kernel_size: int,
p_dropout: int,
resblock: str,
resblock_kernel_sizes: List[int],
resblock_dilation_sizes: List[List[int]],
upsample_rates: List[int],
upsample_initial_channel: int,
upsample_kernel_sizes: List[int],
spk_embed_dim: int,
gin_channels: int,
sr: Union[str, int],
):
super().__init__(
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,
768,
True,
)
class SynthesizerTrnMs256NSFsid_nono(SynthesizerTrnMsNSFsid):
def __init__(
self,
spec_channels: int,
segment_size: int,
inter_channels: int,
hidden_channels: int,
filter_channels: int,
n_heads: int,
n_layers: int,
kernel_size: int,
p_dropout: int,
resblock: str,
resblock_kernel_sizes: List[int],
resblock_dilation_sizes: List[List[int]],
upsample_rates: List[int],
upsample_initial_channel: int,
upsample_kernel_sizes: List[int],
spk_embed_dim: int,
gin_channels: int,
sr=None,
):
super().__init__(
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,
256,
False,
)
class SynthesizerTrnMs768NSFsid_nono(SynthesizerTrnMsNSFsid):
def __init__(
self,
spec_channels: int,
segment_size: int,
inter_channels: int,
hidden_channels: int,
filter_channels: int,
n_heads: int,
n_layers: int,
kernel_size: int,
p_dropout: int,
resblock: str,
resblock_kernel_sizes: List[int],
resblock_dilation_sizes: List[List[int]],
upsample_rates: List[int],
upsample_initial_channel: int,
upsample_kernel_sizes: List[int],
spk_embed_dim: int,
gin_channels: int,
sr=None,
):
super().__init__(
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,
768,
False,
)
|