🍭 Image text recognition service based on Paddle OCR onnx models, compatible with OpenAI's chat/completions API.

PaddleOCR PP-OCRv5 detection + recognition converted to CoreML for Apple Silicon

A modern hard-subtitle recognition tool based on PaddleOCR PP-OCRv5, designed to work seamlessly with the VideoSubFinder subtitle extraction tool. It performs OCR on subtitle images extracted from videos and generates SRT subtitle files. 一个基于PaddleOCR PP-OCRv5的现代化硬字幕识别工具，与VideoSubFinder字幕提取工具完美配合使用。用于对从视频中提取的字幕图片进行OCR识别，最终生成SRT字幕文件。