Transliteration is the process of transferring a word from the alphabet of one language to the alphabet of another. The objective is to obtain a mapping from one system of writing into another, thereby helping people pronounce words and names in foreign languages and giving readers an idea of how words are pronounced by putting them in a familiar alphabet. In this paper, we explore recent trends in transliteration using deep learning models. We then adopt a convolution-networks' seq2seq model developed by Facebook for the Arabic-English transliteration problem, and compare our approach against the previous ones. Our approach builds on recent work by Google and Amazon researchers and improves on previous methods both in the training and prediction steps.