espnet2.gan_tts.vits.loss.KLDivergenceLossWithoutFlow

source

class espnet2.gan_tts.vits.loss.KLDivergenceLossWithoutFlow(*args, **kwargs)

Bases: Module

KL divergence loss without flow.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(m_q: Tensor, logs_q: Tensor, m_p: Tensor, logs_p: Tensor) → Tensor

Calculate KL divergence loss without flow.

• Parameters:
  • m_q (Tensor) – Posterior encoder projected mean (B, H, T_feats).
  • logs_q (Tensor) – Posterior encoder projected scale (B, H, T_feats).
  • m_p (Tensor) – Expanded text encoder projected mean (B, H, T_feats).
  • logs_p (Tensor) – Expanded text encoder projected scale (B, H, T_feats).