Update app.py

app.py

@@ -13,7 +13,7 @@ nltk.download('punkt')
 tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")
 model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn")
 
-# Function to convert DOCX to PDF
+# Function to convert DOCX to PDF with UTF-8 support
 def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"):
     doc = Document(docx_file)
     full_text = []
@@ -23,7 +23,12 @@ def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"):
     # Create a PDF and write the extracted text
     pdf = FPDF()
     pdf.add_page()
-    pdf.set_font("Times", size=12)
+
+    # Set a UTF-8 compatible font (DejaVuSans)
+    pdf.add_font('DejaVu', '', 'DejaVuSans.ttf', uni=True)
+    pdf.set_font("DejaVu", size=12)
+    
+    # Write the content, ensuring UTF-8 encoding is supported
     pdf.multi_cell(190, 10, txt="\n".join(full_text), align='C')
     pdf.output(output_pdf)
     return output_pdf