Are there benchmarks for such kind of tools? How does it handle tables? Different languages?
Nanonets-OCR-s – OCR model that transforms documents into structured markdown
71–80 of 85 posts
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#72Full disclaimer: I work at Nanonets Excited to share Nanonets-OCR-s, a powerful and lightweight (3B) VLM model that converts documents into clean, structured Markdown. This model is trained to understand document structure and content context (like tables, equations, images, plots, watermarks, checkboxes, etc.). Key Features: LaTeX Equation Recognition Converts inline and block-level math into properly formatted LaTe…
Would any of this be able to handle magazine layouts? I've yet to find anything that can follow their fairly random layouts with text at varying angles etc
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#73Full disclaimer: I work at Nanonets Excited to share Nanonets-OCR-s, a powerful and lightweight (3B) VLM model that converts documents into clean, structured Markdown. This model is trained to understand document structure and content context (like tables, equations, images, plots, watermarks, checkboxes, etc.). Key Features: LaTeX Equation Recognition Converts inline and block-level math into properly formatted LaTe…
So it feels like it finally let me do one thing I'd wanted for some time: scan printed documents and generate structured pdfs (and not pdf as a picture container).
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#74Earlier quoted context omitted.
Do check out MyST Markdown ( https://mystmd.org )! Academic publishing is a space that MyST is being used, such as https://www.elementalmicroscopy.com/ via Curvenote. (I'm a MyST contributor)
Do you know why myst got traction, instead of RST which seems to have all the custom tagging and extensibility build in from the beginning?
MyST Markdown (the MD flavour, not the same-named Document Engine) was inspired by ReST. It was created to address the main pain-point of ReST for incoming users (it's not Markdown!).
As a project, the tooling to parse MyST Markdown was built on top of Sphinx, which primarily expects ReST as input. Now, I would not be surprised if most _new_ Sphinx users are using MyST Markdown (but I have no data there!)
Subsequently, the Jupyter Book project that built those tools has pivoted to building a new document engine that's better focused on the use-cases of our audience and leaning into modern tooling.
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#75Earlier quoted context omitted.
They will be extracted in a new line as normal text. It will be the last line.
So I’m left to manually link them up? Have you considered using something like Pandoc’s method of marking them up? Footnotes are a fairly common part of scanned pages, and markdown that doesn’t indicate that a footnote is a footnote can be fairly incomprehensible.
I am lazily posting this all over the thread, but do check out MyST Markdown too! https://mystmd.org. We handle footnotes as a structured object.
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#76Can it extract data from scientific graphs like barcharts, time-series, etc. ?
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#77I created a Powershell script to run this locally on any PDF: https://gist.github.com/kordless/652234bf0b32b02e39cef32c71e... It does work, but it is very slow on my older GPU (Nvidia 1080 8GB). I would say it's taking at least 5 minutes per page right now, but maybe more. Edit: If anyone is interested in trying a PDF to markdown conversion utility built this that is hosted on Cloud Run (with GPU support), let me kno…
Very very interested!
Ok, I have it built but things came up and I'm testing this morning (probably still broken but the code is all there):
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#78I have been looking for something that would ingest a decade of old Word and PowerPoint documents and convert them into a standardized format where the individual elements could be repurposed for other formats. This seems like a critical building block for a system that would accomplish this task. Now I need a catalog, archive, or historian function that archives and pulls the elements easily. Amazing work!
Which decade? DOCX and PPTX is just zipped XMLs, seems pretty standard to me
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#79Full disclaimer: I work at Nanonets Excited to share Nanonets-OCR-s, a powerful and lightweight (3B) VLM model that converts documents into clean, structured Markdown. This model is trained to understand document structure and content context (like tables, equations, images, plots, watermarks, checkboxes, etc.). Key Features: LaTeX Equation Recognition Converts inline and block-level math into properly formatted LaTe…
Have you found it has better accuracy or scales with larger models? Or are the improvements, if any, marginal compared to the 3B VLM model?
Re: Nanonets-OCR-s – OCR model that transforms documents into structured markdown
#80Earlier quoted context omitted.
As anecdotal evidence, it serves my complex-enough purposes very well - mathematics and code interspersed together. One of my "litmus test" papers is this old paper on a Fortran inverse-Laplace transform algorithm [1] that intersperses inline and display equations, and monospace code blocks, while requiring OCR from scratch, and very few models currently do a satisfactory job, i.e. in the following page transcribed b…
Hi, author of marker here - I tried your image, and I don't see the issues you're describing with the newest version of marker (1.7.5). I ran both with no setting specified, and with force_ocr, and I didn't see the issues either time.
Hi there - thanks for getting back to me. I do genuinely want this workflow to work - Marker has been very useful for other purposes for me!
I’m currently using the Datalab online playground with default settings - does that enable inline math recognition?