Update app.py

app.py

@@ -11,23 +11,21 @@ from reportlab.pdfgen import canvas
 
 nltk.download('punkt')
 
-# Load the models and tokenizers once, not every time the function is called
+# Load the models and tokenizers
 tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")
 model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn")
 
-# Function to convert DOCX to PDF using reportlab (UTF-8 compatible)
+# Convert DOCX to PDF using reportlab
 def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"):
     doc = Document(docx_file)
     full_text = []
     for para in doc.paragraphs:
         full_text.append(para.text)
     
-    # Create a PDF and write the extracted text using reportlab
     pdf = canvas.Canvas(output_pdf, pagesize=letter)
     pdf.setFont("Helvetica", 12)
     
-    # Write text line by line
-    text = pdf.beginText(40, 750)  # Start position on the page
+    text = pdf.beginText(40, 750)
     for line in full_text:
         text.textLine(line)
     
@@ -35,29 +33,23 @@ def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"):
     pdf.save()
     return output_pdf
 
-# Main processing function
+# Process input file (PDF or DOCX)
 def pdf_to_text(text, PDF, min_length=20):
     try:
-        # Determine whether the input is a PDF or DOCX
         file_extension = os.path.splitext(PDF.name)[1].lower()
         
-        # If DOCX, first convert it to PDF
         if file_extension == '.docx':
-            pdf_file_path = docx_to_pdf(PDF.name)  # Convert DOCX to PDF
-            text = extract_text(pdf_file_path)  # Extract text from the newly created PDF
-        # If PDF, extract text from it directly
+            pdf_file_path = docx_to_pdf(PDF.name)
+            text = extract_text(pdf_file_path)
         elif file_extension == '.pdf' and text == "":
             text = extract_text(PDF.name)
         
-        # Tokenize text
-        inputs = tokenizer([text], max_length=1024, return_tensors="pt")
+        inputs = tokenizer([text], max_length=1024, truncation=True, return_tensors="pt")
         min_length = int(min_length)
         
-        # Generate summary
         summary_ids = model.generate(inputs["input_ids"], num_beams=2, min_length=min_length, max_length=min_length+1000)
-        output_text = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)[0]
+        output_text = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
         
-        # Save summarized text to PDF
         pdf = FPDF()
         pdf.add_page()
         pdf.set_font("Times", size=12)
@@ -65,7 +57,6 @@ def pdf_to_text(text, PDF, min_length=20):
         pdf_output_path = "legal.pdf"
         pdf.output(pdf_output_path)
         
-        # Convert summarized text to audio
         audio_output_path = "legal.wav"
         tts = gTTS(text=output_text, lang='en', slow=False)
         tts.save(audio_output_path)
@@ -75,35 +66,27 @@ def pdf_to_text(text, PDF, min_length=20):
     except Exception as e:
         return None, f"An error occurred: {str(e)}", None
 
-# Function to process the preloaded document
+# Preloaded document handler
 def process_sample_document(min_length=20):
-    # Replace this with the path to your preloaded legal document (PDF)
     sample_document_path = "Marbury v. Madison.pdf"
     
-    # Simulate file-like object for Gradio
     with open(sample_document_path, "rb") as f:
         return pdf_to_text("", f, min_length)
 
 # Gradio interface
 with gr.Blocks() as iface:
-    # Create a button to process the sample document
     with gr.Row():
-        process_sample_button = gr.Button("Process Sample Legal Document")
+        process_sample_button = gr.Button("Summarize Pre-Uploaded Marbury v. Madison Case Documented")
     
-    # Create the regular input interface
     text_input = gr.Textbox(label="Input Text")
     file_input = gr.File(label="Upload PDF or DOCX")
     slider = gr.Slider(minimum=10, maximum=100, step=10, value=20, label="Summary Minimum Length")
     
-    # Outputs
     audio_output = gr.Audio(label="Generated Audio")
     summary_output = gr.Textbox(label="Generated Summary")
     pdf_output = gr.File(label="Summary PDF")
     
-    # Define the action for the button click to process the preloaded document
     process_sample_button.click(fn=process_sample_document, inputs=slider, outputs=[audio_output, summary_output, pdf_output])
-    
-    # Define the action for the regular file processing
     file_input.change(fn=pdf_to_text, inputs=[text_input, file_input, slider], outputs=[audio_output, summary_output, pdf_output])
 
 if __name__ == "__main__":