Update app.py

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
 import os
-import nltk
 import torch
 from transformers import AutoTokenizer, AutoModel
 from fpdf import FPDF
@@ -9,9 +8,10 @@ from pdfminer.high_level import extract_text
 from docx import Document
 from reportlab.lib.pagesizes import letter
 from reportlab.pdfgen import canvas
+import spacy
 
-nltk.download('punkt')
-from nltk.tokenize import sent_tokenize
+# Load spaCy English model
+nlp = spacy.load("en_core_web_sm")
 
 # Load the LegalBERT model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("nlpaueb/legal-bert-base-uncased")
@@ -33,10 +33,11 @@ def docx_to_pdf(docx_file, output_pdf="converted_doc.pdf"):
     pdf.save()
     return output_pdf
 
-# Extractive summarization using LegalBERT
+# Extractive summarization using LegalBERT and spaCy
 def extractive_summarization(text, num_sentences=5):
-    # Tokenize text into sentences
-    sentences = sent_tokenize(text)
+    # Tokenize text into sentences using spaCy
+    doc = nlp(text)
+    sentences = [sent.text.strip() for sent in doc.sents if sent.text.strip()]
     # Handle case where document has fewer sentences than requested
     num_sentences = min(num_sentences, len(sentences))
     # Encode sentences