Need help with nonauto-nmt?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

238 Stars 43 Forks BSD 3-Clause "New" or "Revised" License 1 Commits 3 Opened issues


PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"

Services available


Need anything else?

Contributors list

Non-Autoregressive Transformer

Code release for Non-Autoregressive Neural Machine Translation by Jiatao Gu, James Bradbury, Caiming Xiong, Victor O.K. Li, and Richard Socher.

Requires PyTorch 0.3, torchtext 0.2.1, and SpaCy.

The pipeline for training a NAT model for a given language pair includes: 1.
for alignment supervision) 2.
(trains an autoregressive model) 3.
(produces the distillation corpus for training the NAT) 4.
(trains the NAT model) 5.
(fine-tunes the NAT model)

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.