The news comes a day after the announcement that Lens, computer vision from Google that works with Google Assistant, will be made available in real time as part of the camera for the Pixel 3 due out November 1. Translations with the camera in Google Translate do not work offline however, the Translate app can be granted access to your photos to carry out translations when you re-establish an internet connection. Optical character recognition from Google Cloud Vision API was used to train new datasets for the 13 languages, a company spokesperson told VentureBeat. ![]() New translation capabilities with computer vision introduced today utilize Neural Machine Translation (NMT), a neural net-driven approach that got an upgrade for better offline translations earlier this year. Translations can be carried out in real time. To carry out visual translations, simply open the Translate app and choose the camera icon. Translation of text seen in photos or in real-time on billboards or menus was added for Google Translate in 2015, and started with 27 languages.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |