/Image2text

Image2Text identifies, classifies and labels video and images for newsrooms. Powered by computer vision models, it recognizes objects and people in video, images and infographics, and labels specific contexts in Spanish and English through natural language. The tool seeks to promote better data governance by including perspectives from the Global South.

Primary LanguageJavaScriptGNU General Public License v3.0GPL-3.0

No issues in this repository yet.