app.py

import streamlit as st
from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
from PIL import Image

# Load the pre-trained model and processor
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
processor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")

# Streamlit app title
st.title("Image to Text App")

# File uploader
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    # Load and display the image
    image = Image.open(uploaded_file)
    st.image(image, caption='Uploaded Image', use_column_width=True)

    # Process the image
    pixel_values = processor(images=image, return_tensors="pt").pixel_values

    # Generate text
    output_ids = model.generate(pixel_values)
    text = tokenizer.decode(output_ids[0], skip_special_tokens=True)

    # Display the generated text
    st.write("Generated Text:")
    st.write(text)