Upload README.md with huggingface_hub

README.md

@@ -9,20 +9,34 @@ tags:
 pipeline_tag: image-to-text
 ---
 
-# Khmer OCR CNN + Transformer
+# Khmer OCR CNN + Transformer (ONNX)
 
-This repository contains a ResNet + Transformer decoder checkpoint for Khmer OCR, I don’t have a public paper for this model — everything comes from thousands of experiments across different model architectures and datasets.
+This repository contains a ResNet + Transformer decoder checkpoint for Khmer OCR,
+the exported ONNX graph, the serialized `config.json` (vocab + hyperparameters),
+and the standalone `inference_onnx.py` helper.
+
+## Files
+
+- `khmer_ocr.onnx` – ONNX model
+- `config.json` – hyperparameters plus serialized vocabulary
+- `inference_onnx.py` and `model.py` – inference helper and architecture
 
-## Installation
-```python
-pip install mer
-```
 ## Usage
+
 ```python
-from mer import Mer
+from huggingface_hub import hf_hub_download
+import importlib.util
+
+repo_id = "metythorn/ocr-stn-cnn-transformer-base"
+onnx_path = hf_hub_download(repo_id=repo_id, filename="khmer_ocr.onnx")
+config_path = hf_hub_download(repo_id=repo_id, filename="config.json")
+inference_path = hf_hub_download(repo_id=repo_id, filename="onnx.py")
 
-model = Mer(markdown=True, device='cuda')
-result = model.predict("sample_image.png")
-print("Predicted text:", result)
+spec = importlib.util.spec_from_file_location("khmer_ocr_infer", inference_path)
+module = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(module)
+ONNXPredictor = module.ONNXPredictor
 
-```
+predictor = ONNXPredictor(model_path=onnx_path, config_path=config_path)
+print(predictor.predict("path/to/image.jpg"))
+```