espnet2.gan_tts.hifigan.loss.MelSpectrogramLoss

source

class espnet2.gan_tts.hifigan.loss.MelSpectrogramLoss(fs: int = 22050, n_fft: int = 1024, hop_length: int = 256, win_length: int | None = None, window: str = 'hann', n_mels: int = 80, fmin: int | None = 0, fmax: int | None = None, center: bool = True, normalized: bool = False, onesided: bool = True, log_base: float | None = 10.0)

Bases: Module

Mel-spectrogram loss.

Initialize Mel-spectrogram loss.

• Parameters:
  • fs (int) – Sampling rate.
  • n_fft (int) – FFT points.
  • hop_length (int) – Hop length.
  • win_length (Optional *[*int ]) – Window length.
  • window (str) – Window type.
  • n_mels (int) – Number of Mel basis.
  • fmin (Optional *[*int ]) – Minimum frequency for Mel.
  • fmax (Optional *[*int ]) – Maximum frequency for Mel.
  • center (bool) – Whether to use center window.
  • normalized (bool) – Whether to use normalized one.
  • onesided (bool) – Whether to use oneseded one.
  • log_base (Optional *[*float ]) – Log base value.

forward(y_hat: Tensor, y: Tensor, spec: Tensor | None = None, use_mse: bool = False) → Tensor

Calculate Mel-spectrogram loss.

• Parameters:
  • y_hat (Tensor) – Generated waveform tensor (B, 1, T).
  • y (Tensor) – Groundtruth waveform tensor (B, 1, T).
  • spec (Optional *[*Tensor ]) – Groundtruth linear amplitude spectrum tensor (B, T, n_fft // 2 + 1). if provided, use it instead of groundtruth waveform.
  • use_l2 (bool) – Whether to use mse_loss instead of l1
• Returns: Mel-spectrogram loss value.
• Return type: Tensor