manga-ocr-base is an open-source OCR model focused on recognizing Japanese text in manga and printed materials. It leverages a Vision Encoder Decoder framework and is suitable for developers, translators, and researchers working with Japanese comics and documents.
In the Foundation models & chat space, Manga Ocr Base takes a focused approach. It provides accurate OCR for Japanese manga and printed text, enabling digitization and translation workflows. It is built as an open-source project for AI developers, manga translators, researchers. Manga Ocr Base is open source under the Apache-2.0 license. The product ships for the web and the command line.
Behind Manga Ocr Base is kha-white, and the product first shipped in 2022. Development happens publicly on GitHub with 2.7k stars. Key capabilities include Japanese OCR, manga text recognition, and Vision Encoder Decoder.
Latest indexed changes and source events
Other apps tracked under the same category.
