File size: 7,329 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 |
# 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/descriptinc/descript-audio-codec/blob/main/dac/model/discriminator.py
import torch
import torch.nn as nn
import torch.nn.functional as F
from audiotools import AudioSignal
from audiotools import ml
from audiotools import STFTParams
from einops import rearrange
from torch.nn.utils import weight_norm
def WNConv1d(*args, **kwargs):
act = kwargs.pop("act", True)
conv = weight_norm(nn.Conv1d(*args, **kwargs))
if not act:
return conv
return nn.Sequential(conv, nn.LeakyReLU(0.1))
def WNConv2d(*args, **kwargs):
act = kwargs.pop("act", True)
conv = weight_norm(nn.Conv2d(*args, **kwargs))
if not act:
return conv
return nn.Sequential(conv, nn.LeakyReLU(0.1))
class MPD(nn.Module):
def __init__(self, period):
super().__init__()
self.period = period
self.convs = nn.ModuleList(
[
WNConv2d(1, 32, (5, 1), (3, 1), padding=(2, 0)),
WNConv2d(32, 128, (5, 1), (3, 1), padding=(2, 0)),
WNConv2d(128, 512, (5, 1), (3, 1), padding=(2, 0)),
WNConv2d(512, 1024, (5, 1), (3, 1), padding=(2, 0)),
WNConv2d(1024, 1024, (5, 1), 1, padding=(2, 0)),
]
)
self.conv_post = WNConv2d(
1024, 1, kernel_size=(3, 1), padding=(1, 0), act=False
)
def pad_to_period(self, x):
t = x.shape[-1]
x = F.pad(x, (0, self.period - t % self.period), mode="reflect")
return x
def forward(self, x):
fmap = []
x = self.pad_to_period(x)
x = rearrange(x, "b c (l p) -> b c l p", p=self.period)
for layer in self.convs:
x = layer(x)
fmap.append(x)
x = self.conv_post(x)
fmap.append(x)
return fmap
class MSD(nn.Module):
def __init__(self, rate: int = 1, sample_rate: int = 44100):
super().__init__()
self.convs = nn.ModuleList(
[
WNConv1d(1, 16, 15, 1, padding=7),
WNConv1d(16, 64, 41, 4, groups=4, padding=20),
WNConv1d(64, 256, 41, 4, groups=16, padding=20),
WNConv1d(256, 1024, 41, 4, groups=64, padding=20),
WNConv1d(1024, 1024, 41, 4, groups=256, padding=20),
WNConv1d(1024, 1024, 5, 1, padding=2),
]
)
self.conv_post = WNConv1d(1024, 1, 3, 1, padding=1, act=False)
self.sample_rate = sample_rate
self.rate = rate
def forward(self, x):
x = AudioSignal(x, self.sample_rate)
x.resample(self.sample_rate // self.rate)
x = x.audio_data
fmap = []
for l in self.convs:
x = l(x)
fmap.append(x)
x = self.conv_post(x)
fmap.append(x)
return fmap
BANDS = [(0.0, 0.1), (0.1, 0.25), (0.25, 0.5), (0.5, 0.75), (0.75, 1.0)]
class MRD(nn.Module):
def __init__(
self,
window_length: int,
hop_factor: float = 0.25,
sample_rate: int = 44100,
bands: list = BANDS,
):
"""Complex multi-band spectrogram discriminator.
Parameters
----------
window_length : int
Window length of STFT.
hop_factor : float, optional
Hop factor of the STFT, defaults to ``0.25 * window_length``.
sample_rate : int, optional
Sampling rate of audio in Hz, by default 44100
bands : list, optional
Bands to run discriminator over.
"""
super().__init__()
self.window_length = window_length
self.hop_factor = hop_factor
self.sample_rate = sample_rate
self.stft_params = STFTParams(
window_length=window_length,
hop_length=int(window_length * hop_factor),
match_stride=True,
)
n_fft = window_length // 2 + 1
bands = [(int(b[0] * n_fft), int(b[1] * n_fft)) for b in bands]
self.bands = bands
ch = 32
convs = lambda: nn.ModuleList(
[
WNConv2d(2, ch, (3, 9), (1, 1), padding=(1, 4)),
WNConv2d(ch, ch, (3, 9), (1, 2), padding=(1, 4)),
WNConv2d(ch, ch, (3, 9), (1, 2), padding=(1, 4)),
WNConv2d(ch, ch, (3, 9), (1, 2), padding=(1, 4)),
WNConv2d(ch, ch, (3, 3), (1, 1), padding=(1, 1)),
]
)
self.band_convs = nn.ModuleList([convs() for _ in range(len(self.bands))])
self.conv_post = WNConv2d(ch, 1, (3, 3), (1, 1), padding=(1, 1), act=False)
def spectrogram(self, x):
x = AudioSignal(x, self.sample_rate, stft_params=self.stft_params)
x = torch.view_as_real(x.stft())
x = rearrange(x, "b 1 f t c -> (b 1) c t f")
# Split into bands
x_bands = [x[..., b[0] : b[1]] for b in self.bands]
return x_bands
def forward(self, x):
x_bands = self.spectrogram(x)
fmap = []
x = []
for band, stack in zip(x_bands, self.band_convs):
for layer in stack:
band = layer(band)
fmap.append(band)
x.append(band)
x = torch.cat(x, dim=-1)
x = self.conv_post(x)
fmap.append(x)
return fmap
class Discriminator(nn.Module):
def __init__(
self,
rates: list = [],
periods: list = [2, 3, 5, 7, 11],
fft_sizes: list = [2048, 1024, 512],
sample_rate: int = 44100,
bands: list = BANDS,
):
"""Discriminator that combines multiple discriminators.
Parameters
----------
rates : list, optional
sampling rates (in Hz) to run MSD at, by default []
If empty, MSD is not used.
periods : list, optional
periods (of samples) to run MPD at, by default [2, 3, 5, 7, 11]
fft_sizes : list, optional
Window sizes of the FFT to run MRD at, by default [2048, 1024, 512]
sample_rate : int, optional
Sampling rate of audio in Hz, by default 44100
bands : list, optional
Bands to run MRD at, by default `BANDS`
"""
super().__init__()
discs = []
discs += [MPD(p) for p in periods]
discs += [MSD(r, sample_rate=sample_rate) for r in rates]
discs += [MRD(f, sample_rate=sample_rate, bands=bands) for f in fft_sizes]
self.discriminators = nn.ModuleList(discs)
def preprocess(self, y):
# Remove DC offset
y = y - y.mean(dim=-1, keepdims=True)
# Peak normalize the volume of input audio
y = 0.8 * y / (y.abs().max(dim=-1, keepdim=True)[0] + 1e-9)
return y
def forward(self, x):
x = self.preprocess(x)
fmaps = [d(x) for d in self.discriminators]
return fmaps
if __name__ == "__main__":
disc = Discriminator()
x = torch.zeros(1, 1, 44100)
results = disc(x)
for i, result in enumerate(results):
print(f"disc{i}")
for i, r in enumerate(result):
print(r.shape, r.mean(), r.min(), r.max())
print()
|