espnet.nets.pytorch_backend.tacotron2.cbhg.CBHGLoss

source

class espnet.nets.pytorch_backend.tacotron2.cbhg.CBHGLoss(use_masking=True)

Bases: Module

Loss function module for CBHG.

Initialize CBHG loss module.

• Parameters:use_masking (bool) – Whether to mask padded part in loss calculation.

forward(cbhg_outs, spcs, olens)

Calculate forward propagation.

• Parameters:
  • cbhg_outs (Tensor) – Batch of CBHG outputs (B, Lmax, spc_dim).
  • spcs (Tensor) – Batch of groundtruth of spectrogram (B, Lmax, spc_dim).
  • olens (LongTensor) – Batch of the lengths of each sequence (B,).
• Returns: L1 loss value Tensor: Mean square error loss value.
• Return type: Tensor