src/models/imageCaptioning.py

from PIL import Image
from transformers import BlipProcessor , BlipForConditionalGeneration
import torch


processor = BlipProcessor.from_pretrained("src/models/Caption")
model = BlipForConditionalGeneration.from_pretrained("src/models/Caption")


def generateCaption(image_path):
    image = Image.open(image_path).convert("RGB")
    inputs = processor(images = image , return_tensors="pt")
    output = model.generate(**inputs)
    caption = processor.decode(output[0], skip_special_tokens = True)
    return caption