Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- kh
|
| 5 |
+
tags:
|
| 6 |
+
- ocr
|
| 7 |
+
- pytorch
|
| 8 |
+
- handwritten
|
| 9 |
+
license: mit
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Kiri OCR Model
|
| 13 |
+
|
| 14 |
+
This is a lightweight OCR model for Kiri OCR, capable of recognizing English and Khmer text.
|
| 15 |
+
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from kiri_ocr.core import OCR
|
| 20 |
+
|
| 21 |
+
# Load from Hugging Face
|
| 22 |
+
ocr = OCR(model_path="mrrtmob/kiri-ocr")
|
| 23 |
+
|
| 24 |
+
# Extract text
|
| 25 |
+
text, results = ocr.extract_text("path/to/image.jpg")
|
| 26 |
+
print(text)
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
## Model Details
|
| 30 |
+
- Architecture: CRNN (CNN + LSTM + CTC)
|
| 31 |
+
- Framework: PyTorch
|
| 32 |
+
- Input Size: Height 32px (width variable)
|