gnurt2041/MangaOCR

A lightweight OCR model for Japanese text, especially in Manga

21
/ 100
Experimental

This tool helps Japanese manga readers, translators, or enthusiasts quickly convert Japanese text from manga images into editable digital text. You input a manga panel image, and it outputs the detected Japanese characters, helping you read, search, or translate the dialogue and narration more efficiently. It's designed for anyone working with or enjoying Japanese manga content.

No commits in the last 6 months.

Use this if you need to extract Japanese text from manga images, especially if you deal with various text orientations, fonts, or text overlaid on complex backgrounds, and prefer a faster, lightweight solution.

Not ideal if you require extremely high accuracy for very long sentences or demand perfect recognition comparable to human transcription, as it's still improving.

manga-translation Japanese-language-study comic-digitization fan-translation Japanese-text-extraction
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

35

Forks

2

Language

Python

License

Category

latex-ocr-tools

Last pushed

May 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gnurt2041/MangaOCR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.