Spaces:
Runtime error
Runtime error
| # -*- coding: utf-8 -*- | |
| # Copyright (c) Facebook, Inc. and its affiliates. | |
| # All rights reserved. | |
| # | |
| # This source code is licensed under the license found in the | |
| # LICENSE file in the root directory of this source tree. | |
| # Original copyright 2019 Tomoki Hayashi | |
| # MIT License (https://opensource.org/licenses/MIT) | |
| import torch | |
| import torch.nn.functional as F | |
| # device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') | |
| """STFT-based Loss modules.""" | |
| def stft(x, fft_size, hop_size, win_length, window): | |
| """Perform STFT and convert to magnitude spectrogram. | |
| Args: | |
| x (Tensor): Input signal tensor (B, T). | |
| fft_size (int): FFT size. | |
| hop_size (int): Hop size. | |
| win_length (int): Window length. | |
| window (str): Window function type. | |
| Returns: | |
| Tensor: Magnitude spectrogram (B, #frames, fft_size // 2 + 1). | |
| """ | |
| x_stft = torch.stft(x[:, 0, :], fft_size, hop_size, win_length, window, return_complex=True) | |
| x_stft = torch.view_as_real(x_stft) | |
| real = x_stft[..., 0] | |
| imag = x_stft[..., 1] | |
| # NOTE(kan-bayashi): clamp is needed to avoid nan or inf | |
| return torch.sqrt(torch.clamp(real ** 2 + imag ** 2, min=1e-7)).transpose(2, 1) | |
| class SpectralConvergengeLoss(torch.nn.Module): | |
| """Spectral convergence loss module.""" | |
| def __init__(self): | |
| """Initilize spectral convergence loss module.""" | |
| super(SpectralConvergengeLoss, self).__init__() | |
| def forward(self, x_mag, y_mag): | |
| """Calculate forward propagation. | |
| Args: | |
| x_mag (Tensor): Magnitude spectrogram of predicted signal (B, #frames, #freq_bins). | |
| y_mag (Tensor): Magnitude spectrogram of groundtruth signal (B, #frames, #freq_bins). | |
| Returns: | |
| Tensor: Spectral convergence loss value. | |
| """ | |
| return torch.norm(y_mag - x_mag, p="fro") / torch.norm(y_mag, p="fro") | |
| class LogSTFTMagnitudeLoss(torch.nn.Module): | |
| """Log STFT magnitude loss module.""" | |
| def __init__(self): | |
| """Initilize los STFT magnitude loss module.""" | |
| super(LogSTFTMagnitudeLoss, self).__init__() | |
| def forward(self, x_mag, y_mag): | |
| """Calculate forward propagation. | |
| Args: | |
| x_mag (Tensor): Magnitude spectrogram of predicted signal (B, #frames, #freq_bins). | |
| y_mag (Tensor): Magnitude spectrogram of groundtruth signal (B, #frames, #freq_bins). | |
| Returns: | |
| Tensor: Log STFT magnitude loss value. | |
| """ | |
| return F.l1_loss(torch.log(y_mag), torch.log(x_mag)) | |
| class STFTLoss(torch.nn.Module): | |
| """STFT loss module.""" | |
| def __init__(self, fft_size=1024, shift_size=120, win_length=600, window="hann_window"): | |
| """Initialize STFT loss module.""" | |
| super(STFTLoss, self).__init__() | |
| self.fft_size = fft_size | |
| self.shift_size = shift_size | |
| self.win_length = win_length | |
| self.register_buffer("window", getattr(torch, window)(win_length)) | |
| self.spectral_convergenge_loss = SpectralConvergengeLoss() | |
| self.log_stft_magnitude_loss = LogSTFTMagnitudeLoss() | |
| def forward(self, x, y): | |
| """Calculate forward propagation. | |
| Args: | |
| x (Tensor): Predicted signal (B, T). | |
| y (Tensor): Groundtruth signal (B, T). | |
| Returns: | |
| Tensor: Spectral convergence loss value. | |
| Tensor: Log STFT magnitude loss value. | |
| """ | |
| x_mag = stft(x, self.fft_size, self.shift_size, self.win_length, self.window) | |
| y_mag = stft(y, self.fft_size, self.shift_size, self.win_length, self.window) | |
| sc_loss = self.spectral_convergenge_loss(x_mag, y_mag) | |
| mag_loss = self.log_stft_magnitude_loss(x_mag, y_mag) | |
| return sc_loss, mag_loss | |
| class MultiResolutionSTFTLoss(torch.nn.Module): | |
| """Multi resolution STFT loss module.""" | |
| def __init__(self, | |
| fft_sizes=(1024, 2048, 512), | |
| hop_sizes=(120, 240, 50), | |
| win_lengths=(600, 1200, 240), | |
| window="hann_window", factor_sc=0.1, factor_mag=0.1): | |
| """Initialize Multi resolution STFT loss module. | |
| Args: | |
| fft_sizes (list): List of FFT sizes. | |
| hop_sizes (list): List of hop sizes. | |
| win_lengths (list): List of window lengths. | |
| window (str): Window function type. | |
| factor (float): a balancing factor across different losses. | |
| """ | |
| super(MultiResolutionSTFTLoss, self).__init__() | |
| assert len(fft_sizes) == len(hop_sizes) == len(win_lengths) | |
| self.stft_losses = torch.nn.ModuleList() | |
| for fs, ss, wl in zip(fft_sizes, hop_sizes, win_lengths): | |
| self.stft_losses += [STFTLoss(fs, ss, wl, window)] | |
| self.factor_sc = factor_sc | |
| self.factor_mag = factor_mag | |
| def forward(self, x, y): | |
| """Calculate forward propagation. | |
| Args: | |
| x (Tensor): Predicted signal (B, T). | |
| y (Tensor): Groundtruth signal (B, T). | |
| Returns: | |
| Tensor: Multi resolution spectral convergence loss value. | |
| Tensor: Multi resolution log STFT magnitude loss value. | |
| """ | |
| sc_loss = 0.0 | |
| mag_loss = 0.0 | |
| for f in self.stft_losses: | |
| sc_l, mag_l = f(x, y) | |
| sc_loss += sc_l | |
| mag_loss += mag_l | |
| sc_loss /= len(self.stft_losses) | |
| mag_loss /= len(self.stft_losses) | |
| return self.factor_sc*sc_loss, self.factor_mag*mag_loss | |
| class L1_Multi_STFT(torch.nn.Module): | |
| """STFT loss module.""" | |
| def __init__(self): | |
| """Initialize STFT loss module.""" | |
| super(L1_Multi_STFT, self).__init__() | |
| self.multi_STFT_loss = MultiResolutionSTFTLoss() | |
| self.l1_loss = torch.nn.L1Loss() | |
| def forward(self, x, y): | |
| """Calculate forward propagation. | |
| Args: | |
| x (Tensor): Predicted signal (B, T). | |
| y (Tensor): Groundtruth signal (B, T). | |
| Returns: | |
| Tensor: Spectral convergence loss value. | |
| Tensor: Log STFT magnitude loss value. | |
| """ | |
| sc_loss, mag_loss = self.multi_STFT_loss(x, y) | |
| l1_loss = self.l1_loss(x, y) | |
| return sc_loss + mag_loss + l1_loss | |
| LOSSES = { | |
| 'mse': torch.nn.MSELoss(), | |
| 'L1': torch.nn.L1Loss(), | |
| 'Multi_STFT': MultiResolutionSTFTLoss(), | |
| 'L1_Multi_STFT': L1_Multi_STFT() | |
| } | |
| def get_loss(loss_config, device): | |
| return LOSSES[loss_config['name']].to(device) | |