# PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend

DevFeed: [PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend](<https://devfeed.tech/articles/paddleocr-3-5-running-ocr-and-document-parsing-tasks-with-a-transformers-backend-7031.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/PaddlePaddle/paddleocr-transformers>)

Author: AlexZhang; Cuicheng; Jun Zhang; Manhui Lin; Yue Zhang

Published: 2026-05-18T15:12:46Z

Content type: release

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [document ai](<https://devfeed.tech/topics/document-ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [document-ai](<https://devfeed.tech/tags/document-ai.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [inference](<https://devfeed.tech/tags/inference.md>), [ocr](<https://devfeed.tech/tags/ocr.md>), [python](<https://devfeed.tech/tags/python.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [rag](<https://devfeed.tech/tags/rag.md>), [rocm](<https://devfeed.tech/tags/rocm.md>), [transformers](<https://devfeed.tech/tags/transformers.md>)

## AI overview

PaddleOCR 3.5 adds Transformers as a supported inference backend for OCR and document parsing models, while PaddleOCR continues to manage the underlying pipelines. The release simplifies integration with Hugging Face-centered environments and downstream document workflows such as RAG, search, analytics, and automation.

## Source excerpt

PaddleOCR continues to provide OCR model series such as PP-OCRv5 and document parsing model series such as PaddleOCR-VL 1.5, while Transformers becomes one of the supported backends for running them. Try the live demo on Hugging Face Spaces: PaddleOCR 3.5 introduces a more flexible inference-engine interface. Developers can select the backend through the parameter and pass backend-specific options through .