hashirama/mote-ocr
hashirama/mote-ocr
Watch
1
1
Fork
You've already forked mote-ocr
 0
Code Issues Pull requests Projects Releases Wiki Activity Actions
a ocr inspired by watamote, meant to be independent and free from bloat
6 commits 3 branches 0 tags 257 MiB
  • Python 79.2%
  • C++ 20.8%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
hashirama f956324616 improve accuracy 
we dont need 3 channels for manga, and in my tests the accuracy was greatly improved by lowering the number of channels to only two (maybe B&W)

this can be related to the fact that some files in the model folder do mention that only two channels are supposed to be used.
2025-04-19 05:28:07 +00:00
inference_test.py improve accuracy 2025-04-19 05:28:07 +00:00
LICENSE Initial commit 2025-04-04 00:16:30 +00:00
README.md Update README.md 2025-04-04 00:18:19 +00:00
silly_decoder.cpp add in-memory processing 2025-04-04 07:13:04 +00:00

README.md

mote-ocr

a ocr inspired by watamote, meant to be independent and free from bloat