app.py

import streamlit as st
from transformers import pipeline

classifier = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
def main():
    st.title("image-to-text")

    with st.form("image"):
        image = st.file_uploader('Choose a file')
        # clicked==True only when the button is clicked
        clicked = st.form_submit_button("Submit")
        if clicked:
          results = classifier([image])
          st.json(results)

if __name__ == "__main__":
    main()
    
"""'audio-classification', 'automatic-speech-recognition', 'conversational', 'document-question-answering', 'feature-extraction', 'fill-mask', 'image-classification', 'image-segmentation', 'image-to-text', 'ner', 'object-detection', 'question-answering', 'sentiment-analysis', 'summarization', 'table-question-answering', 'text-classification', 'text-generation', 'text2text-generation', 'token-classification', 'translation', 'visual-question-answering', 'vqa', 'zero-shot-classification', 'zero-shot-image-classification', 'translation_XX_to_YY'"""