Awesome Open Source
Awesome Open Source

A neural machine translation model written in pytorch.

For a up-to-date PyTorch implementation of basic vanilla attentional NMT, please refer to this repo

With 256-dimensional LSTM hidden size, it achieves a training speed of 14000 words/sec and 26.9 BLEU score on the IWSLT 2014 Germen-English dataset (Ranzato et al., 2015).

File Structure

  • main file
  • script used to generate .bin vocabulary file from parallel corpus
  • script containing helper functions
  •| helper scripts to train|test RAML models with different temperature settings (refer to [Norouzi et al., 2016] for details)


  • Generate Vocabulary Files
  • Vanilla Maximum Likelihood Training
. scripts/
  • Reward Augmented Maximum Likelihood Training (Norouzi et al., 2016)
. scripts/
  • Reinforcement Learning (Coming soon)


  • batched decoding as in openNMT


This work is licensed under a Creative Commons Attribution 4.0 International License.

Alternatives To Pytorch_nmt
Select To Compare

Alternative Project Comparisons
Related Awesome Lists
Top Programming Languages

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (890,046
Machine Learning (40,892
Deep Learning (39,311
Pytorch (22,633
Neural (16,506
Translation (13,668
Nmt (523
Neural Machine Translation (224