surya-ocr

import asyncio from surya.model.surya import SuryaOCR from PIL import Image as PILImage, ImageDraw, ImageFont # Create a dummy image for demonstration def create_dummy_image(): img = PILImage.new('RGB', (800, 600), color = 'white') d = ImageDraw.Draw(img) try: fnt = ImageFont.truetype("arial.ttf", 40) except IOError: fnt = ImageFont.load_default() d.text((50,50), "Hello, Surya OCR!", fill=(0,0,0), font=fnt) d.text((50,150), "This is a test document.", fill=(0,0,0), font=fnt) return img async def main(): print("Loading Surya OCR models...") # This will download models on first run model = SuryaOCR.create_model() print("Models loaded. Creating dummy image...") image = create_dummy_image() print("Running OCR...") # Run OCR (detection, recognition, and layout) # For real use, replace [image] with a list of PIL.Image objects results = await model.ocr([image], languages=["en"]) print("OCR Results:") for page in results: for line in page.text_lines: print(f" Line: '{line.text}', Bbox: {line.bbox}") # Optional: Print words # for word in page.words: # print(f" Word: '{word.text}', Bbox: {word.bbox}") if __name__ == "__main__": asyncio.run(main())