PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters

Summary

PP-OCRv6 is PaddleOCR’s latest universal OCR model family, targeting text detection and recognition across documents, screenshots, displays, labels, and scene text. It offers tiny, small, and medium tiers spanning 1.5M to 34.5M parameters, while the small and medium tiers support 50 languages. Its PPLCNetV4 backbone is shared across detection and recognition, with RepLKFPN for lightweight multi-scale detection and EncoderWithLightSVTR for recognition using local context and global attention. On PaddleOCR’s official in-house multi-scenario benchmarks, PP-OCRv6_medium reaches 86.2% detection Hmean and 83.2% recognition accuracy, improving over PP-OCRv5_server by 4.6 percentage points and 5.1 percentage points. PaddleOCR provides Paddle Inference, Transformers, and ONNX Runtime paths, and results can be saved as visualization images or structured JSON for downstream workflows.

Takeaways

1. 1

   PP-OCRv6_medium has 34.5M parameters, 86.2% detection Hmean, and 83.2% recognition accuracy on PaddleOCR’s official in-house multi-scenario benchmarks.

2. 2

   PP-OCRv6_small and PP-OCRv6_medium support 50 languages, including Simplified Chinese, Traditional Chinese, English, Japanese, and 46 Latin-script languages.

3. 3

   PaddleOCR can run PP-OCRv6 through Paddle Inference, Transformers, or ONNX Runtime, with outputs available as visualization images and structured JSON.