Update app.py

app.py

@@ -11,11 +11,9 @@ from reportlab.pdfgen import canvas
 
 nltk.download('punkt')
 
-# Load the models and tokenizers
 tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")
 model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn")
 
-# Convert DOCX to PDF using reportlab
 def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"):
     doc = Document(docx_file)
     full_text = []
@@ -33,8 +31,7 @@ def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"):
     pdf.save()
     return output_pdf
 
-# Process input file (PDF or DOCX)
-def pdf_to_text(text, PDF, min_length=20):
+def pdf_to_text(text, PDF, min_length=80):  # Increase default min_length by 4 times
     try:
         file_extension = os.path.splitext(PDF.name)[1].lower()
         
@@ -47,8 +44,8 @@ def pdf_to_text(text, PDF, min_length=20):
         inputs = tokenizer([text], max_length=1024, truncation=True, return_tensors="pt")
         min_length = int(min_length)
         
-        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=False)[0]
+        summary_ids = model.generate(inputs["input_ids"], num_beams=2, min_length=min_length, max_length=min_length + 4000)
+        output_text = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]  # Set explicitly
         
         pdf = FPDF()
         pdf.add_page()
@@ -66,21 +63,19 @@ def pdf_to_text(text, PDF, min_length=20):
     except Exception as e:
         return None, f"An error occurred: {str(e)}", None
 
-# Preloaded document handler
-def process_sample_document(min_length=20):
+def process_sample_document(min_length=80):
     sample_document_path = "Marbury v. Madison.pdf"
     
     with open(sample_document_path, "rb") as f:
         return pdf_to_text("", f, min_length)
 
-# Gradio interface
 with gr.Blocks() as iface:
     with gr.Row():
-        process_sample_button = gr.Button("Summarize Pre-Uploaded Marbury v. Madison Case Documented")
+        process_sample_button = gr.Button("Summarize Marbury v. Madison Case Pre-Uploaded")
     
     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=100, label="Summary Minimum Length")
+    slider = gr.Slider(minimum=10, maximum=400, step=10, value=80, label="Summary Minimum Length")  # Default value set to 80
     
     audio_output = gr.Audio(label="Generated Audio")
     summary_output = gr.Textbox(label="Generated Summary")