⚡ RapidOCR Benchmark (PP-OCRv4 — ONNX Runtime)
Benchmark RapidOCR with the lightweight ONNX Runtime inference backend on public OCR datasets.
| Property | Value |
|---|---|
| Engine | RapidOCR (rapidocr-onnxruntime) |
| Model version | PP-OCRv4 (ONNX exported) |
| Runtime | ONNX Runtime |
| AWS Lambda zip (250 MB)? | ⚠️ Tight — run benchmark to see actual size |
| AWS Lambda container (10 GB)? | ✅ Fits easily |
📏 Deployment sizes are measured from actual installed files on disk — not pip metadata.
💡 Compare with the PaddleOCR benchmark Space to see how the full PaddlePaddle runtime compares.
Run RapidOCR on a benchmark dataset and measure accuracy, speed & deployment footprint.
Select Benchmark Dataset
5 50
Metrics