espnet2.legacy.nets.pytorch_backend.e2e_tts_tacotron2.Tacotron2Loss

source

class espnet2.legacy.nets.pytorch_backend.e2e_tts_tacotron2.Tacotron2Loss(use_masking=True, use_weighted_masking=False, bce_pos_weight=20.0)

Bases: Module

Loss function module for Tacotron2.

Initialize Tactoron2 loss module.

• Parameters:
  • use_masking (bool) – Whether to apply masking for padded part in loss calculation.
  • use_weighted_masking (bool) – Whether to apply weighted masking in loss calculation.
  • bce_pos_weight (float) – Weight of positive sample of stop token.

forward(after_outs, before_outs, logits, ys, labels, olens)

Calculate forward propagation.

• Parameters:
  • after_outs (Tensor) – Batch of outputs after postnets (B, Lmax, odim).
  • before_outs (Tensor) – Batch of outputs before postnets (B, Lmax, odim).
  • logits (Tensor) – Batch of stop logits (B, Lmax).
  • ys (Tensor) – Batch of padded target features (B, Lmax, odim).
  • labels (LongTensor) – Batch of the sequences of stop token labels (B, Lmax).
  • olens (LongTensor) – Batch of the lengths of each target (B,).
• Returns: L1 loss value. Tensor: Mean square error loss value. Tensor: Binary cross entropy loss value.
• Return type: Tensor