Upload README.md with huggingface_hub

README.md

@@ -20,6 +20,13 @@ The recognition dictionary is Chinese + English (6,904 characters), so Latin
 text, digits and punctuation decode natively; Japanese, Korean, Cyrillic and
 Arabic are not covered.
 
+| Input — `samples/sample.jpg` | NPU output — boxes + recognized text |
+|:---:|:---:|
+| <img src="https://huggingface.co/Synaptics/paddle-paddle-tiny/resolve/main/samples/sample.jpg" width="380"> | <img src="https://huggingface.co/Synaptics/paddle-paddle-tiny/resolve/main/assets/sample_ocr.jpg" width="380"> |
+
+All ten lines are read correctly at confidence ≥ 0.966, in 1.7 s end to end on
+an SL2619.
+
 ## Files
 
 | File | Purpose |
@@ -33,7 +40,6 @@ Arabic are not covered.
 | `ppocr_det_dynamic.onnx` | fp32 detection, CPU reference for accuracy checks |
 | `ppocr_rec_dynamic.onnx` | fp32 recognition, CPU reference for accuracy checks |
 | `samples/sample.jpg` | Sample café menu card, 10 text lines |
-| `samples/sample.png` | Sample document page, 99 text lines |
 
 ### Why four recognition models
 
@@ -66,13 +72,16 @@ NPU output against a CPU reference.
 
 ## Measured on SL2619
 
-| Sample | Lines | Detection | Recognition |
-|---|---|---|---|
-| `sample.jpg` (menu card, 912×1200) | 10 | ~0.52 s | ~1.2 s |
-| `sample.png` (paper page, 1224×1584) | 99 | ~0.70 s | ~22.2 s |
+`samples/sample.jpg`, 912×1200, 10 text lines detected:
+
+| Stage | Time |
+|---|---|
+| Detection (800×608) | ~0.53 s |
+| Recognition (10 lines, bucketed) | ~1.19 s |
 
-Recognition scales with line count because each line is a separate invocation —
-the bucket models are compiled with a static batch of 1.
+Recognition scales with the number of detected lines, because each line is a
+separate invocation — the bucket models are compiled with a static batch of 1.
+A dense page of 99 lines takes roughly 22 s.
 
 ### About `sample.jpg`