Create app.py

app.py

@@ -0,0 +1,51 @@
+import streamlit as st
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+from pdfminer.high_level import extract_text
+
+def main():
+    st.title("PDF Translation")    
+    # Upload the pdf
+    uploaded_file = st.file_uploader("Upload a PDF file and we will translate the text inside to German and French", type=["pdf"])
+
+    if uploaded_file is not None:
+        # Extract text from pdf
+        text = 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
+        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():
+            # Translate the entire text, not page by page
+            text_to_translate = prefix + text
+            input_ids = tokenizer(text_to_translate, return_tensors="pt").input_ids
+            outputs = model.generate(input_ids=input_ids, max_length=150, num_beams=4, no_repeat_ngram_size=2)
+            translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+            translations[language] = translated_text
+
+        # Display the translations based on the button clicked
+        if translate_german:
+            display_translation(translations["german"], "German")
+
+        if translate_french:
+            display_translation(translations["french"], "French")
+
+
+def display_translation(translation, language):
+    st.write(f"\nLanguage: {language}")
+    st.write(f"Translation:\n {translation}")
+
+
+if __name__ == "__main__":
+    main()