Provides a RETURNN wrapper around warp-transducer:

Importing this module immediately compiles the library and TF module.


Checks if the git submodule is checkout out.

Return type:



Initializes and compiles the library. Caches the TF module.


verbose (bool)

returnn.extern.WarpRna.rna_loss(log_probs, labels, input_lengths, label_lengths, blank_label=0)[source]

Computes the RNA loss between a sequence of activations and a ground truth labeling. Args:

log_probs: A 4-D Tensor of floats. The dimensions

should be (B, T, U, V), where B is the minibatch index, T is the time index, U is the prediction network sequence length, and V indexes over activations for each symbol in the alphabet.

labels: A 2-D Tensor of ints, shape (B,U-1) a padded label sequences to make sure

labels for the minibatch are same length.

input_lengths: A 1-D Tensor of ints, shape (B,), the number of time steps

for each sequence in the minibatch.

label_lengths: A 1-D Tensor of ints, shape (B,), the length of each label

for each example in the minibatch.

blank_label: int, scalar, the label value/index that the RNA

calculation should use as the blank label


1-D float Tensor, the cost of each example in the minibatch (as negative log probabilities).