-
Internal export: (pseudo PageXML)
- [x] All regions are `RegionLayout` with `category` attribute (saved to XML as TextRegion element with category in custom attribute)
- [x] Set OCR/OMR Engines to …
-
First of all, amazing work, guys. I am blown away by the project.
I was just wondering if you could possibly integrate PDF export as a last workflow step?
That last step would be really integral to …
-
Since the last update I am getting
```
09:12:50.405 INFO eynollah - INPUT FILE PHYS_0001 (1/3)
09:12:50.972 INFO eynollah - Resizing and enhancing image...
09:12:50.972 INFO eynollah - Detected 3…
-
* for simple files: how do we make sure that files with same filename from different folders don't get overwritten?
* for PAGE: at the moment, output_dir only defines the dir for extended predictions
-
I am using https://github.com/UB-Mannheim/ocr-fileformat which includes the prima-page-converter.
Given [this file](https://files.gitter.im/609272e76da03739847bdbf8/s5U8/10.1515_zfrs-1980-0101.xml)…
-
Hi Rutger and other people of the Loghi-community,
Thank you for your great work on Loghi and the underlying set of tooling.
This post is not really an issue, but more of a question. We're maki…
-
I am on Calamari 2.2.2, and when freely combining the arguments I see on `--help` …
```
calamari-eval --checkpoint hsbfraktur.cala/best.ckpt.json --gt.preload false --n_worst_lines 10 --gt.texts /…
-
Example input, gzip'd, base64:
```
QlpoOTFBWSZTWQ0I/UwAAvTfgERUUGf/97/n3sC/7//6UAVedhYMQaNAaaXQklNMRNU80yaan6ph
Q9J6mnlB6mjRtRoPKepoyAaSNT0j9UAMjQZAA00GgGgAAAkSVNlPSeoaA0xDQyMQDQyA0AaGg4yZ
MmIxMAJ…
-
For TR 2.0, untangle a project (repblic?) using plain-text i.s.o. segmented_text
-
I've cloned all the files from github to the computer. The instructions state that to use the file protocol Firefox must be utilized. I've tried to reach it but whenever I give in the protocol plus th…