app.py

import gradio as gr
from transformers import pipeline

image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")


def generate_caption(img):
  caption = image_to_text(img)
  return caption[0]['generated_text']


demo = gr.Interface(
    fn = generate_caption,
    inputs = gr.Image(type = 'filepath'),
    outputs = gr.Textbox(lines = 2),
)
demo.launch()