Spaces:
Running
Running
File size: 7,926 Bytes
3dd84f8 |
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 |
from functools import partial
from math import prod
from typing import Callable
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import Conv1d
from torch.nn.utils.parametrizations import weight_norm
from torch.nn.utils.parametrize import remove_parametrizations
from torch.utils.checkpoint import checkpoint
def init_weights(m, mean=0.0, std=0.01):
classname = m.__class__.__name__
if classname.find("Conv") != -1:
m.weight.data.normal_(mean, std)
def get_padding(kernel_size, dilation=1):
return (kernel_size * dilation - dilation) // 2
class ResBlock1(torch.nn.Module):
def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
super().__init__()
self.convs1 = nn.ModuleList(
[
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=dilation[0],
padding=get_padding(kernel_size, dilation[0]),
)
),
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=dilation[1],
padding=get_padding(kernel_size, dilation[1]),
)
),
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=dilation[2],
padding=get_padding(kernel_size, dilation[2]),
)
),
]
)
self.convs1.apply(init_weights)
self.convs2 = nn.ModuleList(
[
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=1,
padding=get_padding(kernel_size, 1),
)
),
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=1,
padding=get_padding(kernel_size, 1),
)
),
weight_norm(
Conv1d(
channels,
channels,
kernel_size,
1,
dilation=1,
padding=get_padding(kernel_size, 1),
)
),
]
)
self.convs2.apply(init_weights)
def forward(self, x):
for c1, c2 in zip(self.convs1, self.convs2):
xt = F.silu(x)
xt = c1(xt)
xt = F.silu(xt)
xt = c2(xt)
x = xt + x
return x
def remove_parametrizations(self):
for conv in self.convs1:
remove_parametrizations(conv)
for conv in self.convs2:
remove_parametrizations(conv)
class ParralelBlock(nn.Module):
def __init__(
self,
channels: int,
kernel_sizes: tuple[int] = (3, 7, 11),
dilation_sizes: tuple[tuple[int]] = ((1, 3, 5), (1, 3, 5), (1, 3, 5)),
):
super().__init__()
assert len(kernel_sizes) == len(dilation_sizes)
self.blocks = nn.ModuleList()
for k, d in zip(kernel_sizes, dilation_sizes):
self.blocks.append(ResBlock1(channels, k, d))
def forward(self, x):
return torch.stack([block(x) for block in self.blocks], dim=0).mean(dim=0)
class HiFiGANGenerator(nn.Module):
def __init__(
self,
*,
hop_length: int = 512,
upsample_rates: tuple[int] = (8, 8, 2, 2, 2),
upsample_kernel_sizes: tuple[int] = (16, 16, 8, 2, 2),
resblock_kernel_sizes: tuple[int] = (3, 7, 11),
resblock_dilation_sizes: tuple[tuple[int]] = ((1, 3, 5), (1, 3, 5), (1, 3, 5)),
num_mels: int = 128,
upsample_initial_channel: int = 512,
use_template: bool = True,
pre_conv_kernel_size: int = 7,
post_conv_kernel_size: int = 7,
post_activation: Callable = partial(nn.SiLU, inplace=True),
):
super().__init__()
assert (
prod(upsample_rates) == hop_length
), f"hop_length must be {prod(upsample_rates)}"
self.conv_pre = weight_norm(
nn.Conv1d(
num_mels,
upsample_initial_channel,
pre_conv_kernel_size,
1,
padding=get_padding(pre_conv_kernel_size),
)
)
self.num_upsamples = len(upsample_rates)
self.num_kernels = len(resblock_kernel_sizes)
self.noise_convs = nn.ModuleList()
self.use_template = use_template
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(
nn.ConvTranspose1d(
upsample_initial_channel // (2**i),
upsample_initial_channel // (2 ** (i + 1)),
k,
u,
padding=(k - u) // 2,
)
)
)
if not use_template:
continue
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))
self.resblocks.append(
ParralelBlock(ch, resblock_kernel_sizes, resblock_dilation_sizes)
)
self.activation_post = post_activation()
self.conv_post = weight_norm(
nn.Conv1d(
ch,
1,
post_conv_kernel_size,
1,
padding=get_padding(post_conv_kernel_size),
)
)
self.ups.apply(init_weights)
self.conv_post.apply(init_weights)
def forward(self, x, template=None):
x = self.conv_pre(x)
for i in range(self.num_upsamples):
x = F.silu(x, inplace=True)
x = self.ups[i](x)
if self.use_template:
x = x + self.noise_convs[i](template)
if self.training and self.checkpointing:
x = checkpoint(
self.resblocks[i],
x,
use_reentrant=False,
)
else:
x = self.resblocks[i](x)
x = self.activation_post(x)
x = self.conv_post(x)
x = torch.tanh(x)
return x
def remove_parametrizations(self):
for up in self.ups:
remove_parametrizations(up)
for block in self.resblocks:
block.remove_parametrizations()
remove_parametrizations(self.conv_pre)
remove_parametrizations(self.conv_post)
|