Metadata-Version: 2.1
Name: manga-ocr
Version: 0.1.6
Summary: OCR for Japanese manga
Home-page: https://github.com/kha-white/manga-ocr
Author: Maciej Budyś
Author-email: kha-white@mail.com
License: Apache License 2.0
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Description-Content-Type: text/markdown
License-File: LICENSE

# Manga OCR

Optical character recognition for Japanese text, with the main focus being Japanese manga.
It uses a custom end-to-end model built with Transformers' [Vision Encoder Decoder](https://huggingface.co/docs/transformers/model_doc/visionencoderdecoder) framework. 

Manga OCR can be used as a general purpose printed Japanese OCR, but its main goal was to provide a high quality
text recognition, robust against various scenarios specific to manga:
- both vertical and horizontal text
- text with furigana
- text overlaid on images
- wide variety of fonts and font styles
- low quality images

Unlike many OCR models, Manga OCR supports recognizing multi-line text in a single forward pass,
so that text bubbles found in manga can be processed at once, without splitting them into lines.

See also:
- Development code, including code for training and synthetic data generation: [link](manga_ocr_dev)
- Description of synthetic data generation pipeline + examples of generated images: [link](manga_ocr_dev/synthetic_data_generator)



