[Regression] Lack of Slice Parameter

[karanataryn]

🔎 Search before asking

• I have searched the PaddleOCR Docs and found no similar bug report.
• I have searched the PaddleOCR Issues and found no similar bug report.
• I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

Similar to the discussion here: #14677, we need a slice parameter to be able to handle large input images and files. Otherwise, PaddleOCR drops important text.

🏃‍♂️ Environment (运行环境)

Debian Linux x86, Python 3.11.2, PaddleOCR 3.0.2

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

Run reader.predict() on the above image after initialize a PaddleOCR reader.