Groups Similar Search Look up By Text Browse About

Google Translate is rolling out offline AI-based translations that you can download


Google has rolled out offline downloads for its AI-powered translator. So if you dont have unlimited data or you have a plan that doesnt work internationally, you can now download neural machine translation from Googles Android and iOS apps. Previously, you could download Google Translates offline dictionary on the go. But whether you were figuring your way through a foreign menu or deciphering cool storefronts, you may have discovered that the dictionarys quite literal translations dont fully grasp the nuances of a foreign language, even if the language is Spanish or French, which are quite similar to English. The plight doubles when youre trying to decipher a language with a different alphabet and roots, like Russian or Chinese, where even the AI-based translator makes mistakes. Google Translates offline AI translations will first be available in 59 languages, including English, Arabic, Chinese, German, and Hindi, to name a few. Theyll take about 35MB per language, so they wont use up too much of your devices storage. Lower-specced phones should also be able to support the new update, as Google says it wants users in all markets to have access to the feature. Its a gradual rollout; about 1 percent of Google Translate users will get the update today. By the 13th, 99 percent of users should get the update, and by the 15th, it should be fully available. No more strange literal dictionary definitions while traveling, for the most part. Heres a full list of the 59 available languages: 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, Lavtian, 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

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.