OCR and document AI
Reading PDFs, scans and tables with models, and how to check the result.
18 links, newest first.
- OCR and document AIRepository
Open-source classifier for tax document pages
The GitHub project is a tax document page classifier built on Jev decisions. Its description claims 100% strict accuracy across 261 IRS forms at about $0.001 per page.
Engineers can inspect an open-source approach to classifying tax document pages and its reported accuracy and cost.
- OCR and document AIPost on X
WeVisDoc and jina-ocr-v1 are new OCR models
The post reports Tencent’s WeVisDoc 2B and 4B models under Apache 2.0 and jinaai’s jina-ocr-v1 under a non-commercial license. It says WeVisDoc-4B scores 95.38 on OmniDocBench v1.6, while NaviDC-OCR is current SOTA.
The model options, license terms, and benchmark result help engineers compare OCR candidates.
- OCR and document AIRepository
iOS OCR server using Apple’s Vision framework
The open-source iOS-OCR-Server project uses Apple’s Vision framework to provide OCR from an iPhone. The post describes local processing and an API for use by devices on the same network.
It offers engineers a way to explore on-device OCR through a network-accessible API.
- OCR and document AIRepository
Testing Unlimited OCR Against an OCR Benchmark
The author says Baidu Unlimited OCR was added to mlx-vlm and plans to test it against an OCR benchmark. The post also asks for other strong OCR benchmarks.
Engineers evaluating OCR models can use the linked benchmark as a starting point.
- OCR and document AIRepository
Unlimited OCR for Long Documents
Baidu’s open-source OCR model uses Reference Sliding Window Attention to process documents longer than 40 pages in one forward pass. The post reports 3B total parameters, 500M activated, and results on OmniDocBench v1.5 and v1.6.
Engineers can inspect the implementation of an approach to long-document OCR with constant KV Cache size.
- OCR and document AIRepository
PaddleOCR 3.7 adds ONNX Runtime support
PaddleOCR 3.7 adds an ONNX Runtime inference backend and support for CPU inference via OpenVINO and GPU inference via CUDA and TensorRT. The post says PP-OCRv6 models are up to 3.9× faster on CPU.
Engineers can compare inference backends and hardware options when deploying OCR across platforms.
- OCR and document AIRepository
PaddleOCR releases PP-OCRv6 model series
PP-OCRv6 includes Tiny, Small, and Medium models ranging from 1.5M to 34.5M parameters. PaddlePaddle reports support for 50 languages, new OCR scenarios, and up to 5.2× faster CPU inference with OpenVINO.
Engineers can compare model sizes, language coverage, and inference options for OCR deployments.
- OCR and document AIPost on X
Baidu releases PP-OCRv6 for multilingual OCR
The post says PP-OCRv6 comes in 1.5M, 7.7M, and 34.5M parameter sizes, supports 48+ languages and several text types, and is designed for edge deployment.
The model-size options and stated text coverage may help engineers assess it for OCR workloads.
- OCR and document AIPost on X
PaddleOCR-VL 1.6 reports 96.33% on OmniDocBench v1.6
The post announces PaddleOCR-VL 1.6 and reports a 96.33% score on OmniDocBench v1.6, which it describes as a new state of the art.
The benchmark result may help engineers track OCR model performance on document understanding.
- OCR and document AIModel
GLM-OCR: a 0.9B multimodal OCR model
The post announces GLM-OCR, described as a 0.9B model using a multimodal GLM-V architecture and an MIT license. The author claims it ranks first on OmniDocBench v1.5 with a score of 94.62.
Engineers evaluating OCR models can inspect its model page and compare the reported benchmark claim.
- OCR and document AIArticle
Ente’s on-device OCR for Android
Ente describes how it brought private, on-device text recognition to Ente Photos. The post says its OCR is fully open source.
Useful as an implementation example for engineers exploring private, on-device OCR.
- OCR and document AIModel
Tencent releases the 1B-parameter Hunyuan OCR model
Tencent’s end-to-end document-understanding model supports document parsing, visual question answering, and translation. The post links to its Hugging Face model and an interactive demo.
Engineers can evaluate a document AI model across parsing, visual Q&A, and translation tasks.
- OCR and document AIRepository
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.
- OCR and document AIPost on X
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.
- OCR and document AIPost on X
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.
- OCR and document AIPost on X
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.
- OCR and document AIPost on X
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.
Build with AgentLog
Send your own newsletter
CommsHarbor keeps contacts, consent and one-click unsubscribe together.
Free workspace
Open CommsHarbor