63 lines
2.0 KiB
Python
63 lines
2.0 KiB
Python
from typing import Dict, List
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
import torchaudio.transforms as T
|
|
|
|
|
|
class MultiResolutionSTFTLoss(nn.Module):
|
|
"""
|
|
Computes a loss based on multiple STFT resolutions, including both
|
|
spectral convergence and log STFT magnitude components.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
fft_sizes: List[int] = [1024, 2048, 512],
|
|
hop_sizes: List[int] = [120, 240, 50],
|
|
win_lengths: List[int] = [600, 1200, 240],
|
|
eps: float = 1e-7,
|
|
):
|
|
super().__init__()
|
|
self.stft_transforms = nn.ModuleList(
|
|
[
|
|
T.Spectrogram(
|
|
n_fft=n_fft, win_length=win_len, hop_length=hop_len, power=None
|
|
)
|
|
for n_fft, hop_len, win_len in zip(fft_sizes, hop_sizes, win_lengths)
|
|
]
|
|
)
|
|
self.eps = eps
|
|
|
|
def forward(
|
|
self, y_true: torch.Tensor, y_pred: torch.Tensor
|
|
) -> Dict[str, torch.Tensor]:
|
|
sc_loss = 0.0 # Spectral Convergence Loss
|
|
mag_loss = 0.0 # Log STFT Magnitude Loss
|
|
|
|
for stft in self.stft_transforms:
|
|
stft.to(y_pred.device) # Ensure transform is on the correct device
|
|
|
|
# Get complex STFTs
|
|
stft_true = stft(y_true)
|
|
stft_pred = stft(y_pred)
|
|
|
|
# Get magnitudes
|
|
stft_mag_true = torch.abs(stft_true)
|
|
stft_mag_pred = torch.abs(stft_pred)
|
|
|
|
# --- Spectral Convergence Loss ---
|
|
# || |S_true| - |S_pred| ||_F / || |S_true| ||_F
|
|
norm_true = torch.linalg.norm(stft_mag_true, dim=(-2, -1))
|
|
norm_diff = torch.linalg.norm(stft_mag_true - stft_mag_pred, dim=(-2, -1))
|
|
sc_loss += torch.mean(norm_diff / (norm_true + self.eps))
|
|
|
|
# --- Log STFT Magnitude Loss ---
|
|
mag_loss += F.l1_loss(
|
|
torch.log(stft_mag_pred + self.eps), torch.log(stft_mag_true + self.eps)
|
|
)
|
|
|
|
total_loss = sc_loss + mag_loss
|
|
return {"total": total_loss, "sc": sc_loss, "mag": mag_loss}
|