| license: apache-2.0 | |
| language: | |
| - ur | |
| tags: | |
| - ocr | |
| - urdu | |
| - vision | |
| - unsloth | |
| base_model: unsloth/DeepSeek-OCR | |
| # Urdu OCR Model - اردو او سی آر | |
| Fine-tuned DeepSeek-OCR model for Urdu text recognition. | |
| ## Model Description | |
| This model is fine-tuned on Urdu text images for optical character recognition (OCR) tasks. | |
| ## Usage | |
| ```python | |
| from unsloth import FastVisionModel | |
| from transformers import AutoModel | |
| model, tokenizer = FastVisionModel.from_pretrained( | |
| "nomypython/urdu-ocr-deepseek", | |
| load_in_4bit=True, | |
| auto_model=AutoModel, | |
| trust_remote_code=True, | |
| ) | |
| FastVisionModel.for_inference(model) | |
| result = model.infer( | |
| tokenizer, | |
| prompt="<image>\nExtract Urdu text from this image:", | |
| image_file="your_image.png", | |
| image_size=640, | |
| base_size=640, | |
| crop_mode=False, | |
| ) | |
| print(result) | |
| ``` | |
| ## Training Details | |
| - Base Model: DeepSeek-OCR | |
| - Fine-tuned for: Urdu OCR | |
| - Framework: Unsloth | |
| - LoRA Rank: 16 | |
| ## Intended Use | |
| Extract Urdu text from images containing printed or handwritten text. | |