donut
tessdoc
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
donut
-
Ask HN: Why are all OCR outputs so raw?
maybe this is better? https://github.com/clovaai/donut
I'm not sure
-
Show HN: BetterOCR combines and corrects multiple OCR engines with an LLM
Yup! But I'm still exploring options. (any recommendations would be welcomed!) Here are some candidates I'm considering:
- https://github.com/mindee/doctr
- https://github.com/open-mmlab/mmocr
- https://github.com/PaddlePaddle/PaddleOCR (honestly I don't know Mandarin so I'm a bit stuck)
- https://github.com/clovaai/donut - While it's primarily an "OCR-free document understanding transformer," I think it's worth experimenting with. Think I can sort this out by letting the LLM reason through it multiple times (although this will impact performance)
- yesterday got a suggestion to consider https://github.com/kakaobrain/pororo - I don't think development is still active but the results are pretty great on Korean text
-
New to ML, looking for some GPU and learning material info
I am also interested in experimenting with something like DONUT (https://github.com/clovaai/donut) but I have never seen anything on what the VRAM expectations are for something like this. Does anyone know also if there are any newer better models than this for document parsing as well? Or what the VRAM requirements for something like this tend to be?
-
[D] Is there a good ai model for image-to-text where the images are diagrams and screenshots of interfaces?
Here are a few useful resources you could start with: [Pix2Struct by Google Research](https://github.com/google-research/pix2struct) might be a valuable tool, although it will most likely need some fine-tuning to fit your specifics. You can also find some fine-tuned models on HuggingFace by searching 'pix2struct'. Another option worth considering is [DonutI](https://github.com/clovaai/donut). Like Pix2Struct, fine-tuning likely needed to meet your requirements. Tesseract OCR is another alternative, particularly for handling text. It's primarily designed for pages of text, think books, but with some tweaking and specific flags, it can process tables as well as text chunks in regions of a screenshot. Bit too much tweaking for my taste. As I'm also in search of OCR tools for UI and chart screenshots, so share if you find something else.
- How to Automate Document Extraction from Insurance Documents
- FLaNK Stack Weekly 29 may 2023
- Donut: OCR-Free Document Understanding Transformer
tessdoc
-
Chat with any GPT right through your favorite text editor
Tesseract Documentation
- Any way to convert my handwritten diary to searchable PDFs?
-
Has anyone done OCR using C++? If so, how? I need to implement OCR in a project I am making to store numberplates
You should look for an OCR library, for example https://github.com/tesseract-ocr/tessdoc
-
Advanced Adobe Acrobat OCR features?
With scanned documents, the greatest utility is going to come from treating them as images instead of pdfs, and preprocessing the images to help the OCR algorithm. When a pdf program does OCR, it first tries to "cheat" by reading hard-coded strings, then it uses image analysis for everything else. Any OCR program is going to apply image processing that the authors think work for as many cases as possible, but if you have bespoke documents, preprocessing is the way. Here are some general strategies: https://github.com/tesseract-ocr/tessdoc/blob/main/ImproveQuality.md
-
Program to scan digitized old photos, scrape the datestamp if there is one, and append filename with that date?
If a command-line OCR package like Tesseract is able to read the date from your image files, it should be quite doable to string together a PowerShell script that does what you want.
-
Tesseract Teaser
https://github.com/tesseract-ocr/tessdoc/blob/master/Improve...
What are some alternatives?
PaddleOCR - Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
image-to-sound-python- - A python project for converting an Image into audible sound using OCR and speech synthesis
qlora - QLoRA: Efficient Finetuning of Quantized LLMs
Multi-Type-TD-TSR - Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition:
CascadeTabNet - This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"
deepdoctection - A Repo For Document AI
DocumentInformationExtraction - Key Information Extraction From Documents: Evaluation And Generator
edenai-python - The best AI engines in one API: vision, text, speech, translation, OCR, machine learning, etc. SDK and examples for Python developers.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
DripLoader - Evasive shellcode loader for bypassing event-based injection detection (PoC)
doctr - docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.