Vik Paruchuri comments

Results 136 comments of


                                            Vik Paruchuri

Extraction from 2 column text, marker mixes left and right colum text paragraphs.

I honestly haven't looked into PDF format versions, so I don't know if that is it. That's an interesting find, though. It may also be related to whether the data...

Extraction from 2 column text, marker mixes left and right colum text paragraphs.

I'm currently working on a better way to detect columns that might be useful for this

Extraction from 2 column text, marker mixes left and right colum text paragraphs.

This should be fixed in the new version (coming in the next couple of weeks).

Extraction from 2 column text, marker mixes left and right colum text paragraphs.

Try the dev branch if you're having issues - there is better ordering implemented there, but still have to test more before merging.

DRAFT: Add Dockerfile

Thank you for this, @gardner ! Is there any easy way to get this to work with or without a cuda device? I imagine it would need a different base...

Notebook?

Will merge a demo gradio app as well shortly

Urdu Text Does Not Get Detected

Try the new code/model - `pip install -U surya`

Urdu Text Does Not Get Detected

This seems to work and You may need to experiment with the threshold settings to detect more text (see README)

setup instructions for Windows

Thanks for this! This doesn't seem to include some dependencies: - `ocrmypdf` - `tesseract` + language packs - ghostscript Did you find how to install these?

setup instructions for Windows

Thanks for looking into this! The new version has no required system dependencies, so Windows install should be much simpler - https://github.com/VikParuchuri/marker/pull/116