espnet.nets.pytorch_backend.e2e_tts_fastspeech.FeedForwardTransformerLoss

source

class espnet.nets.pytorch_backend.e2e_tts_fastspeech.FeedForwardTransformerLoss(use_masking=True, use_weighted_masking=False)

Bases: Module

Loss function module for feed-forward Transformer.

Initialize feed-forward Transformer loss module.

• Parameters:
  • use_masking (bool) – Whether to apply masking for padded part in loss calculation.
  • use_weighted_masking (bool) – Whether to weighted masking in loss calculation.

forward(after_outs, before_outs, d_outs, ys, ds, ilens, 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).
  • d_outs (Tensor) – Batch of outputs of duration predictor (B, Tmax).
  • ys (Tensor) – Batch of target features (B, Lmax, odim).
  • ds (Tensor) – Batch of durations (B, Tmax).
  • ilens (LongTensor) – Batch of the lengths of each input (B,).
  • olens (LongTensor) – Batch of the lengths of each target (B,).
• Returns: L1 loss value. Tensor: Duration predictor loss value.
• Return type: Tensor