app.py

import streamlit as st
from transformers import T5Tokenizer, T5ForConditionalGeneration
from pathlib import Path
from pdfminer.high_level import extract_text

def main():
    st.title("PDF Translation")
    st.write("Upload a PDF file and we will translate the text inside to German and French.")
    
    # Upload the pdf
    uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])

    if uploaded_file is not None:
        # Extract text from pdf
        documents = extract_text(uploaded_file)
        tokenizer = T5Tokenizer.from_pretrained("t5-small")
        model = T5ForConditionalGeneration.from_pretrained("t5-small")

        # Define translation prefixes for each language
        translation_prefixes = {
            "german": "translate English to German: ",
            "french": "translate English to French: "
        }

        # Generate translations for each language for each document
        translations = {}

        # Buttons to trigger translation
        translate_german = st.button("Translate to German")
        translate_french = st.button("Translate to French")

        for language, prefix in translation_prefixes.items():
            document_translations = []

            for idx, document in enumerate(documents, 1):
                text = prefix + document.text
                input_ids = tokenizer(text, return_tensors="pt").input_ids
                outputs = model.generate(input_ids=input_ids, max_length=50, num_beams=4, no_repeat_ngram_size=2)
                translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
                document_translations.append(translated_text)

            translations[language] = document_translations

        # Display the translations based on the button clicked
        if translate_german:
            display_translations(translations["german"], "German")

        if translate_french:
            display_translations(translations["french"], "French")


def display_translations(translations, language):
    st.write(f"\nLanguage: {language}")
    for idx, translation in enumerate(translations, 1):
        st.write(f"Page {idx}: {translation}")


if __name__ == "__main__":
    main()