OCR and document AI
- OCR and document AIProject
Qwen3-VL 8B and 30B Compared for OCR
An OCR and structured data extraction comparison of Qwen3-VL 8B BF16 and 30B Q8. The author reports that the quantized 30B model was faster and more accurate, but used more memory.
The comparison highlights trade-offs between model size, quantization, speed, accuracy, and memory for document extraction.
- 1 year ago @allen_ai
olmOCR 2 Uses Verifiable Rewards for Document OCR
The post introduces olmOCR 2, a model for converting PDFs and scans into clean text, with support for tables, equations, and handwriting. It says the model uses synthetic data and unit tests as verifiable rewards.
The approach may interest engineers evaluating OCR for challenging documents and ways to verify model output.
- OCR and document AIArticle
Choosing and Deploying Open OCR Models
A Hugging Face blog post covers choosing an OCR model, comparing bleeding-edge models, deploying locally or remotely, and going beyond OCR.
Useful guidance for engineers evaluating and deploying open models in OCR pipelines.
- 1 year ago @HKydlicek
FinePdfs releases OCR datasets, models, and source code
FinePdfs is releasing its full source code, OCR-Annotations with 1.6k labeled PDFs, Gemma-LID-Annotation with 20k samples per language, and XGB-OCR, an OCR classifier for PDFs.
The datasets and classifier may help engineers build or evaluate PDF OCR workflows.
- 1 year ago @rohanpaul_ai
Zerox extracts structured data from documents with vision models
The post describes Zerox as an open-source OCR and document extraction project. It supports extracting specific information into a structured format using a schema, rather than converting the full document to Markdown.
Schema-based extraction can help engineers retrieve targeted fields from documents.
- 1 year ago @allen_ai
olmOCR extracts plain text from PDFs
AllenAI introduces olmOCR, an open-source tool for extracting plain text from PDFs. The post says it handles many document types and can run on a GPU.
Engineers evaluating PDF text-extraction pipelines can investigate an open-source alternative.
