@TeksEdge: Need to OCR documents? PP-OCRv6 dropped — currently the best open-source OCR models you can download ◆︎ Fully Open Sour…
Summary
PP-OCRv6 is a new open-source OCR model series from Baidu's PaddleOCR, available in Tiny/Small/Medium sizes with excellent accuracy and speed, beating several commercial models.
View Cached Full Text
Cached at: 06/13/26, 01:06 AM
Need to OCR documents? PP-OCRv6 dropped — currently the best open-source OCR models you can download
◆︎ Fully Open Source (Apache 2.0) ◆︎ Excellent accuracy + speed ◆︎ Tiny / Small / Medium sizes (as small as 1.5M params) ◆︎ Strong on complex text, tables, multilingual & industrial docs
Beats: › Gemini 3.1 Pro › GPT-5.5 › Qwen3-VL-235B › Kimi-K2.6 › MiniMax-M3
How PP-OCRv6 Works: It is built on the PaddlePaddle deep learning framework (from Baidu). You need to use the PaddleOCR toolkit to run it.
PaddlePaddle (@PaddlePaddle): 🚀PP-OCRv6 is officially released！
🔥PaddleOCR’s new OCR model series scales from 1.5M to 34.5M parameters, bringing stronger accuracy, faster inference, and broader deployment options — from browsers and edge devices to servers.
📊What’s new: 🔸Tiny / Small / Medium models:
Similar Articles
@AdinaYakup: PP-OCRv6 just released by Baidu @PaddlePaddle tiny 1.5M / small 7.7M / medium 34.5M 48+ languages Supports handwritten/…
Baidu's PaddlePaddle released PP-OCRv6, an OCR model supporting 48+ languages with tiny (1.5M), small (7.7M), and medium (34.5M) sizes, optimized for edge deployment and handwritten/printed/industrial/screen/card text.
🚀PP-OCRv6 is officially released !
PaddleOCR releases PP-OCRv6, a new OCR model series with sizes from 1.5M to 34.5M parameters, offering improved accuracy and faster inference, supporting 50 languages and new scenarios like PCB and CAD drawings, under Apache 2.0 open source license.
PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
PaddleOCR 3.5 adds a Transformers inference backend, enabling OCR and document parsing models like PP-OCRv5 and PaddleOCR-VL 1.5 to run seamlessly within the Hugging Face ecosystem.
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
PaddleOCR-VL-1.6 improves document parsing by identifying and refining under-optimized regions via targeted data optimization and progressive post-training, achieving state-of-the-art 96.33% on OmniDocBench v1.6.
@DailyDoseOfDS_: Fine-tune DeepSeek-OCR on your own language! (100% local) Most vision models treat documents as massive sequences of to…
DeepSeek-OCR is a 3B vision model using context optical compression for efficient document processing. Fine-tuning it on Persian text using Unsloth achieved an 88.26% improvement in character error rate, all open-source and runnable on a single GPU.