Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq

25 May 2018Oleksii KuchaievBoris GinsburgIgor GitmanVitaly LavrukhinJason LiHuyen NguyenCarl CasePaulius Micikevicius

We present OpenSeq2Seq - a TensorFlow-based toolkit for training sequence-to-sequence models that features distributed and mixed-precision training. Benchmarks on machine translation and speech recognition tasks show that models built using OpenSeq2Seq give state-of-the-art performance at 1.5-3x less training time... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.