Layer normalization module. :param int nout: output dim size :param int dim: dimension to be normalized

This module produces sinusoidal positional embeddings of any length. Padding symbols are ignored.

Encoder based on a user-supplied vocabulary (file or list).

Override the forward call in lightning so it goes to training and validation step respectively

Override the forward call in lightning so it goes to training and validation step respectively

Duration predictor module. This is a module of duration predictor described in `FastSpeech: Fast, Robust and Controllable Text to Speech`_.

Loss function module for duration predictor. The loss value is Calculated in log domain to make it Gaussian.

Length regulator module for feed-forward Transformer. This is a module of length regulator described in `FastSpeech: Fast, Robust and Controllabl

An optimized version of nn.Conv1d. At training time, this module uses ConvTBC, which is an optimized version of Conv1d. At inference time,

Encodes each byte to an id. For 8-bit strings only.

Encodes each byte to an id and appends the EOS token.

Revert gradient without any further input modification.

A dataset that provides helpers for batching.

Base class for converting from ints to/from human readable strings.

A dataset that provides helpers for batching.