kha-white/manga-ocr-base

Model

180

stars

6

commits

9

repos using this model

4

linked in READMEs

Jun 22, 2022

updated

endpoints_compatible
image-text-to-text
image-to-text
pytorch
transformers
vision-encoder-decoder
Browse cluster: Document Understanding & OCR Models

README

Manga OCR

Optical character recognition for Japanese text, with the main focus being Japanese manga.

It uses Vision Encoder Decoder 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

Code is available here.

Contributors

kha-white

3 commits

aalhendi

1 commits

MB
Maciej Budyś

1 commits

system

1 commits

kha-white/manga-ocr-base

Model

180

stars

6

commits

9

repos using this model

4

linked in READMEs

Jun 22, 2022

updated

endpoints_compatible
image-text-to-text
image-to-text
pytorch
transformers
vision-encoder-decoder
Browse cluster: Document Understanding & OCR Models

README

Manga OCR

Optical character recognition for Japanese text, with the main focus being Japanese manga.

It uses Vision Encoder Decoder 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

Code is available here.

Contributors

kha-white

3 commits

aalhendi

1 commits

MB
Maciej Budyś

1 commits

system

1 commits