-
Notifications
You must be signed in to change notification settings - Fork 18
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.
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
Failed to load any lstm-specific dictionaries for lang #223
Comments
This is just a warning, it means that the tesseract model doesn't have language model features, just the trained neural network, which is fine.
You mean that the font of your terminal doesn't print these characters? Try a more complete Unicode font like those in the nerd-fonts project |
Is ist possible and necessary to add a language model features? |
It is possible, see e.g. tesseract-ocr/tesstrain#155 (comment) on how to do it with tesstrain. It is not necessary and there is little to be gained with these dictionaries in place. They were more important in the pre-LSTM rule-based models but AFAIK nobody bothers with them when training tesseract 4+ models. |
Ok. Thank you |
hey, tryed to create pdf as output file and get an error: Cannot open file "/.../ocrd_all/venv/share/tessdata//pdf.ttf"! The command I used: tesseract -l Fraktur_50000000.334_450937 input.tif output pdf Any ideas? |
EDIT No, we actually do install all that correctly. But your error message contains a leading slash, which hints at a wrong |
What do mean with a wrong VIRTUAL_ENV setting? |
It's suspicious that tesseract tries to look in |
output of echo $VIRTUAL_ENV: /home/superman/ocrd_all/venv output ls -la $VIRTUAL_ENV/share/tessdata: |
Hi,
I am trying to use stweil's GT4HistOCR model (from https://ocr-d.de/en/models.html) with the following command:
tesseract 00000005.tif 00000005 -l Fraktur_50000000.334_450937
I get the following error message: Failed to load any lstm-specific dictionaries for lang ...
The ocr recognition runs anyway. The Problem is that some characters are recognized correctly but are not displayed properly, e.g.: Hoͤring / Verſuche / uͤber / laͤnger
How to fix this problem?
Thanks
The text was updated successfully, but these errors were encountered: