Skip to content

Issues: tesseract-ocr/tesstrain

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
45 Open 233 Closed
45 Open 233 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Devanagari script box files not being generated
#6 by Shreeshrii was closed May 4, 2018 updated May 4, 2018
2
The dependency from proto-model on data/unicharset does not work
#2 by wrznr was closed May 8, 2018 updated May 8, 2018
@kba
1
License
#5 by amitdo was closed May 8, 2018 updated May 8, 2018
1
generate_line_box should be py 2/3 agnostic
#10 by kba was closed Jun 7, 2018 updated Jun 7, 2018
[Question] High error rate after training - why?
#13 by jovargas was closed Jul 3, 2018 updated Jul 5, 2018
3
cannot run make leptonica tesseract langdata
#16 by orangebacked was closed Jul 19, 2018 updated Jul 19, 2018
1
make training problem
#17 by orangebacked was closed Jul 27, 2018 updated Jul 27, 2018
1
Can it be used on Windows?
#9 by yzy1996 was closed Jul 27, 2018 updated Jul 27, 2018
3
Incorrect train/eval split bug Something isn't working
#19 by lorenzob was closed Aug 23, 2018 updated Aug 23, 2018
1
Adding box file for whole page results a very high Error rate duplicate This issue or pull request already exists
#21 by engahmed1190 was closed Aug 23, 2018 updated Aug 23, 2018
3
unicode error python
#18 by orangebacked was closed Jul 27, 2018 updated Aug 30, 2018
1
Box files contain the same box for all characters question Further information is requested
#25 by RanAR90 was closed Sep 20, 2018 updated Sep 20, 2018
@wrznr
3
Add support for finetuning
#14 by Shreeshrii was closed Dec 3, 2018 updated Dec 3, 2018
3
Finish implementation of finetuning (i.e. CONTINUE_FROM) bug Something isn't working
#33 by wrznr was closed Dec 3, 2018 updated Dec 3, 2018
@kba @wrznr
Remove dependency from langdata repo. enhancement New feature or request
#34 by wrznr was closed Dec 3, 2018 updated Dec 3, 2018
1
@kba
Rename GT directory enhancement New feature or request
#35 by wrznr was closed Dec 3, 2018 updated Dec 3, 2018
@kba
Add exception handling for empty GT files bug Something isn't working
#41 by wrznr was closed Dec 13, 2018 updated Dec 13, 2018
@kba @wrznr
Make training model failed with illegal line count -- 0
#45 by andymishra was closed Dec 17, 2018 updated Dec 17, 2018
1
Make training model question Further information is requested
#31 by atharmarajah was closed Dec 14, 2018 updated Dec 17, 2018
@wrznr
17
finetuning
#46 by soldierofhell was closed Dec 20, 2018 updated Dec 20, 2018
1
make training problem with example dataset
#47 by ofnanezn was closed Jan 7, 2019 updated Jan 7, 2019
3
Update README.md
#39 by wrznr was closed Jan 8, 2019 updated Jan 8, 2019
@kba @wrznr
Generated .box files have identical coordinates for every character duplicate This issue or pull request already exists question Further information is requested
#32 by jaddoughman was closed Jan 8, 2019 updated Jan 8, 2019
@wrznr
31
make langdata
#49 by MrDrProfK was closed Jan 30, 2019 updated Jan 30, 2019
1
Training data from scratch gives error rate alomst 100% and very less ocr accuracy
#51 by jayawantkarale was closed Feb 8, 2019 updated Feb 8, 2019
1
ProTip! What’s not been updated in a month: updated:<2024-05-29.