vidi-deshp/clip-gpt2-finetuned

Fine-Tuned CLIP-GPT2 Model for Image Captioning

This is a fine-tuned version of CLIP-GPT2 for real-time image captioning to aid the visually impaired.

Model Details:

• Base Model: CLIP ViT-B/32
• Fine-Tuned On: VizWiz dataset
• Format: SafeTensors
• Usage:

  from transformers import CLIPProcessor, CLIPModel
  from PIL import Image
  
  model = CLIPModel.from_pretrained("vidi-deshp/clip-gpt2-finetuned")
  processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
  
  image = Image.open("sample.jpg")
  inputs = processor(images=image, return_tensors="pt")
  
  outputs = model(**inputs)