---
license: cc-by-nc-3.0
pipeline_tag: image-to-text
tags:
- vision
- ocr
- trocr
- transformers
- handwriting-recognition
- document-processing
---

# Tzefa Word OCR Model (Fine-tuned TrOCR)

Fine-tuned TrOCR model for recognizing individual handwritten Tzefa keywords.

## Architecture
- **Base model:** `microsoft/trocr-small-stage1`
- **Fine-tuned on:** Handwritten Tzefa keywords (uppercase Hebrew programming commands, number words, variable names)
- **Framework:** HuggingFace Transformers (`VisionEncoderDecoderModel`)

## Vocabulary
Tzefa keywords include:
- **Commands:** MAKEINTEGER, MAKESTR, MAKELIST, MAKEBOOL, PRINTINTEGER, PRINTSTR, ADD, SUBTRACT, MULTIPLY, DIVIDE, WHILETRUE, IFTRUE, etc.
- **Number words:** ZERO through ONEHUNDRED
- **User-defined variable names**

## Usage
```python
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image

# use_fast=False is required to prevent tokenizer conversion crash
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-small-stage1", use_fast=False)
model = VisionEncoderDecoderModel.from_pretrained("WARAJA/Tzefa-Word-OCR-TrOCR")

image = Image.open("word_crop.png").convert("RGB")
pixel_values = processor(image, return_tensors="pt").pixel_values

generated_ids = model.generate(pixel_values)
text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(text)
```

## Related
- [Full Tzefa Pipeline](https://huggingface.co/spaces/WARAJA/Tzefa)
- [OCR Demo](https://huggingface.co/spaces/WARAJA/Tzefa-OCR)
- [Word OCR Dataset](https://huggingface.co/datasets/WARAJA/Tzefa-Word-OCR-Dataset)