themethdev commited on
Commit
0dbca46
Β·
verified Β·
1 Parent(s): da308bd

Create README.md

Browse files

# TrOCR Large Handwritten - ONNX

This is an ONNX conversion of Microsoft's [trocr-large-handwritten](https://huggingface.co/microsoft/trocr-large-handwritten) model, optimized for web deployment and edge inference.

## πŸ“ Model Description

**TrOCR (Transformer-based Optical Character Recognition)** is a state-of-the-art model for handwritten text recognition. This ONNX version enables:

- ⚑ **Web deployment** with [Transformers.js](https://huggingface.co/docs/transformers.js)
- πŸš€ **Edge inference** with ONNX Runtime
- πŸ“± **Cross-platform** compatibility (Web, Node.js, Mobile)

## πŸ”§ Usage

### Web (Transformers.js)

```javascript
import { pipeline } from '@huggingface/transformers';

const captioner = await pipeline('image-to-text', 'mdevst/trocr-large-handwritten');

// Use with image
const result = await captioner('path/to/handwritten/image.jpg');
console.log(result[0].generated_text);
```

### Node.js (ONNX Runtime)

```javascript
const ort = require('onnxruntime-node');

// Load the model
const session = await ort.InferenceSession.create('./model.onnx');

// Run inference
const results = await session.run(feeds);
```

### Python (ONNX Runtime)

```python
from optimum.onnxruntime import ORTModelForVision2Seq
from transformers import TrOCRProcessor
from PIL import Image

# Load model and processor
model = ORTModelForVision2Seq.from_pretrained('mdevst/trocr-large-handwritten')
processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-handwritten')

# Process image
image = Image.open('handwritten_text.jpg')
pixel_values = processor(image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
```

## πŸ“Š Model Performance

- **Original Model Size**: ~2.23GB
- **ONNX Model Size**: ~4.7GB

## 🎯 Use Cases

- ✍️ Handwritten document digitization
- πŸ“ Note transcription
- πŸ” OCR for historical documents
- πŸ“± Mobile text recognition apps
- 🌐 Web-based OCR services

## ⚑ Performance Tips
- Enable **WebGPU** for faster inference in browsers
- **Batch processing** for multiple images
- **Image preprocessing** for better accuracy

## πŸ™ Credits

- **Original Model**: Microsoft Research
- **Paper**: [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282)
- **ONNX Conversion**: Converted using πŸ€— Optimum
- **Framework**: Built with πŸ€— Transformers

## πŸ› Issues & Support

For issues related to:
- **Original model**: [Microsoft TrOCR Issues](https://huggingface.co/microsoft/trocr-large-handwritten/discussions)
- **ONNX conversion**: Open an issue in this repository
- **Transformers.js**: [Transformers.js Issues](https://github.com/huggingface/transformers.js/issues)

Files changed (1) hide show
  1. README.md +9 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - microsoft/trocr-large-handwritten
4
+ pipeline_tag: image-to-text
5
+ library_name: transformers
6
+ tags:
7
+ - trocr
8
+ - vision-encoder-decoder
9
+ ---