Spaces:
Sleeping
Sleeping
File size: 6,588 Bytes
f1069cc |
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 |
import torch
import torch.nn.functional as F
import numpy as np
from scipy.signal import get_window
from librosa.util import pad_center, tiny
from librosa.filters import mel as librosa_mel_fn
from audioldm.audio.audio_processing import (
dynamic_range_compression,
dynamic_range_decompression,
window_sumsquare,
)
class STFT(torch.nn.Module):
"""adapted from Prem Seetharaman's https://github.com/pseeth/pytorch-stft"""
def __init__(self, filter_length, hop_length, win_length, window="hann"):
super(STFT, self).__init__()
self.filter_length = filter_length
self.hop_length = hop_length
self.win_length = win_length
self.window = window
self.forward_transform = None
scale = self.filter_length / self.hop_length
fourier_basis = np.fft.fft(np.eye(self.filter_length))
cutoff = int((self.filter_length / 2 + 1))
fourier_basis = np.vstack(
[np.real(fourier_basis[:cutoff, :]), np.imag(fourier_basis[:cutoff, :])]
)
forward_basis = torch.FloatTensor(fourier_basis[:, None, :])
inverse_basis = torch.FloatTensor(
np.linalg.pinv(scale * fourier_basis).T[:, None, :]
)
if window is not None:
assert filter_length >= win_length
# get window and zero center pad it to filter_length
fft_window = get_window(window, win_length, fftbins=True)
fft_window = pad_center(fft_window, filter_length)
fft_window = torch.from_numpy(fft_window).float()
# window the bases
forward_basis *= fft_window
inverse_basis *= fft_window
self.register_buffer("forward_basis", forward_basis.float())
self.register_buffer("inverse_basis", inverse_basis.float())
def transform(self, input_data):
device = self.forward_basis.device
input_data = input_data.to(device)
num_batches = input_data.size(0)
num_samples = input_data.size(1)
self.num_samples = num_samples
# similar to librosa, reflect-pad the input
input_data = input_data.view(num_batches, 1, num_samples)
input_data = F.pad(
input_data.unsqueeze(1),
(int(self.filter_length / 2), int(self.filter_length / 2), 0, 0),
mode="reflect",
)
input_data = input_data.squeeze(1)
forward_transform = F.conv1d(
input_data,
torch.autograd.Variable(self.forward_basis, requires_grad=False),
stride=self.hop_length,
padding=0,
)#.cpu()
cutoff = int((self.filter_length / 2) + 1)
real_part = forward_transform[:, :cutoff, :]
imag_part = forward_transform[:, cutoff:, :]
magnitude = torch.sqrt(real_part**2 + imag_part**2)
phase = torch.autograd.Variable(torch.atan2(imag_part.data, real_part.data))
return magnitude, phase
def inverse(self, magnitude, phase):
device = self.forward_basis.device
magnitude, phase = magnitude.to(device), phase.to(device)
recombine_magnitude_phase = torch.cat(
[magnitude * torch.cos(phase), magnitude * torch.sin(phase)], dim=1
)
inverse_transform = F.conv_transpose1d(
recombine_magnitude_phase,
torch.autograd.Variable(self.inverse_basis, requires_grad=False),
stride=self.hop_length,
padding=0,
)
if self.window is not None:
window_sum = window_sumsquare(
self.window,
magnitude.size(-1),
hop_length=self.hop_length,
win_length=self.win_length,
n_fft=self.filter_length,
dtype=np.float32,
)
# remove modulation effects
approx_nonzero_indices = torch.from_numpy(
np.where(window_sum > tiny(window_sum))[0]
)
window_sum = torch.autograd.Variable(
torch.from_numpy(window_sum), requires_grad=False
)
window_sum = window_sum
inverse_transform[:, :, approx_nonzero_indices] /= window_sum[
approx_nonzero_indices
]
# scale by hop ratio
inverse_transform *= float(self.filter_length) / self.hop_length
inverse_transform = inverse_transform[:, :, int(self.filter_length / 2) :]
inverse_transform = inverse_transform[:, :, : -int(self.filter_length / 2) :]
return inverse_transform
def forward(self, input_data):
self.magnitude, self.phase = self.transform(input_data)
reconstruction = self.inverse(self.magnitude, self.phase)
return reconstruction
class TacotronSTFT(torch.nn.Module):
def __init__(
self,
filter_length,
hop_length,
win_length,
n_mel_channels,
sampling_rate,
mel_fmin,
mel_fmax,
):
super(TacotronSTFT, self).__init__()
self.n_mel_channels = n_mel_channels
self.sampling_rate = sampling_rate
self.stft_fn = STFT(filter_length, hop_length, win_length)
mel_basis = librosa_mel_fn(
sampling_rate, filter_length, n_mel_channels, mel_fmin, mel_fmax
)
mel_basis = torch.from_numpy(mel_basis).float()
self.register_buffer("mel_basis", mel_basis)
def spectral_normalize(self, magnitudes, normalize_fun):
output = dynamic_range_compression(magnitudes, normalize_fun)
return output
def spectral_de_normalize(self, magnitudes):
output = dynamic_range_decompression(magnitudes)
return output
def mel_spectrogram(self, y, normalize_fun=torch.log):
"""Computes mel-spectrograms from a batch of waves
PARAMS
------
y: Variable(torch.FloatTensor) with shape (B, T) in range [-1, 1]
RETURNS
-------
mel_output: torch.FloatTensor of shape (B, n_mel_channels, T)
"""
assert torch.min(y.data) >= -1, torch.min(y.data)
assert torch.max(y.data) <= 1, torch.max(y.data)
magnitudes, phases = self.stft_fn.transform(y)
magnitudes = magnitudes.data
mel_output = torch.matmul(self.mel_basis, magnitudes)
mel_output = self.spectral_normalize(mel_output, normalize_fun)
energy = torch.norm(magnitudes, dim=1)
log_magnitudes = self.spectral_normalize(magnitudes, normalize_fun)
return mel_output, log_magnitudes, energy
|