Trocr Nepali

🚀 Devanagari OCR with TrOCR

This model is designed for Devanagari Optical Character Recognition (OCR). It's based on the VisionEncoderDecoder architecture and fine - tuned on Nepali/Devanagari script. It uses Hugging Face's TrOCRProcessor to process images and generate text.

🚀 Quick Start

This Devanagari OCR model based on the VisionEncoderDecoder architecture has been fine - tuned on Nepali/Devanagari script. It leverages the TrOCRProcessor from Hugging Face to handle image - to - text conversion.

✨ Features

• Model: syubraj/TrOCR_Nepali
• Processor: TrOCRProcessor, which combines a Vision Transformer (ViT) feature extractor and a tokenizer.

📦 Installation

The installation steps are not provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import VisionEncoderDecoderModel, TrOCRProcessor, AutoTokenizer
from PIL import Image
import torch

# Load the model and processor
tokenizer = AutoTokenizer.from_pretrained("syubraj/TrOCR_Nepali")
model = VisionEncoderDecoderModel.from_pretrained("syubraj/TrOCR_Nepali")
processor = TrOCRProcessor.from_pretrained("syubraj/TrOCR_Nepali")

# Load image
image = Image.open("path_to_image").convert("RGB")

# Preprocess image
pixel_values = processor(image, return_tensors="pt").pixel_values

# Generate text
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(generated_text)

Advanced Usage

The original document doesn't provide advanced usage examples, so this subsection is skipped.

📚 Documentation

The original document doesn't have more detailed documentation, so this section is skipped.

🔧 Technical Details

The original document doesn't have specific technical implementation details (more than 50 words), so this section is skipped.

📄 License

The original document doesn't have license information, so this section is skipped.