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).

Base class for conditional flow matching methods. This class implements the independent conditional flow matching methods from [1] and serves as a

LSTM without worrying about the hidden state, nor the layout of the data. Expects input as convolutional layout.

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

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

Albergo et al. 2023 trigonometric interpolants class. This class inherits the ConditionalFlowMatcher and override the compute_mu_t and compute_con