Groups Similar Search Look up By Text Browse About

Google improves Translate with offline AI

Get accurate language conversion without an internet connection. Google isn't going to sit idly by while Microsoft brings AI-based offline translation to your phone. The company is rolling out internet-free neural machine translation to its Translate apps for Android and iOS, promising much more accurate language conversion when you don't have the luxury of data. The initial release covers 58 languages, including a slew of European and Indian languages as well as common translation targets like Arabic, Chinese and Japanese. Despite the improved accuracy, the app shouldn't chew up too much of your valuable device space. Each language takes about 30MB to 40MB , Google said. And you don't need a powerful device, either -- this should work with "low-end" phones. The smarter offline feature is only available for about one percent of all Translate users as of today, but it should reach 99 percent of them by the 13th and everyone by the 15th. So long as you don't need it right away, you should have everything you need to find the washrooms on your next vacation.

Google brings offline neural machine translations for 59 languages to its Translate app

Currently, when the Google Translate apps for iOS and Android has access to the internet, its translations are far superior to those it produces when its offline. Thats because the offline translations are phrase-based, meaning they use an older machine translation technique than the machine learning-powered systems in the cloud that the app has access to when its online. But thats changing today. Google is now rolling out offline Neural Machine Translation (NMT) support for 59 languages in the Translate apps. Today, only a small number of users will see the updated offline translations, but it will roll out to all users within the next few weeks. The list of supported languages consists of a wide range of languages. Because I dont want to play favorites, here is the full list: Afrikaans, Albanian, Arabic, Belarusian, Bengali, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian, Creole, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Jannada, Korean, Latvian, Lithuanian, Macedonian, Malay, Maltese, Marathi, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese and Welsh. In the past, running these deep learning models on a mobile device wasnt really an option since mobile phones didnt have the right hardware to efficiently run them. Now, thanks to both advances in hardware and software, thats less of an issue and Google, Microsoft and others have also found ways to compress these models to a manageable size. In Googles case, thats about 30 to 40 megabytes per language. Its worth noting that Microsoft also announced a similar feature for its Translator app earlier this year. It uses a very similar technique, but for the time being, it only supports about a dozen languages.