Commit
•
977f308
1
Parent(s):
fd80248
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,18 +8,6 @@ datasets:
|
|
| 8 |
duplicated_from: kha-white/manga-ocr-base
|
| 9 |
---
|
| 10 |
|
| 11 |
-
|
| 12 |
-
|
| 13 |
Optical character recognition for Japanese text, with the main focus being Japanese manga.
|
| 14 |
|
| 15 |
-
It uses [Vision Encoder Decoder](https://huggingface.co/docs/transformers/model_doc/vision-encoder-decoder) framework.
|
| 16 |
-
|
| 17 |
-
Manga OCR can be used as a general purpose printed Japanese OCR, but its main goal was to provide a high quality
|
| 18 |
-
text recognition, robust against various scenarios specific to manga:
|
| 19 |
-
- both vertical and horizontal text
|
| 20 |
-
- text with furigana
|
| 21 |
-
- text overlaid on images
|
| 22 |
-
- wide variety of fonts and font styles
|
| 23 |
-
- low quality images
|
| 24 |
-
|
| 25 |
-
Code is available [here](https://github.com/kha-white/manga_ocr).
|
|
|
|
| 8 |
duplicated_from: kha-white/manga-ocr-base
|
| 9 |
---
|
| 10 |
|
| 11 |
+
[Original Model](https://huggingface.co/kha-white/manga-ocr-base)
|
|
|
|
| 12 |
Optical character recognition for Japanese text, with the main focus being Japanese manga.
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|