Update app.py

app.py

@@ -16,11 +16,10 @@ import docx2txt
 from io import StringIO
 from PyPDF2 import PdfFileReader
 import warnings
-import nltk
+import nltk.data
 
-nltk.download()
+tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
 
-from nltk import sent_tokenize
 warnings.filterwarnings("ignore")
 
 
@@ -71,7 +70,7 @@ def article_text_extractor(url: str):
  
 def chunk_clean_text(text):
 
-    sentences = sent_tokenize(text)
+    sentences = tokenizer(text)
     current_chunk = 0
     chunks = []