Update app.py

app.py

@@ -6,12 +6,14 @@ import numpy
 import scipy
 from gtts import gTTS
 from io import BytesIO
+from transformers import BartTokenizer
 
 def extract_text(pdf_file):
     pdfReader = PyPDF2.PdfReader(pdf_file)
     pageObj = pdfReader.pages[0]
     return pageObj.extract_text()
 
+
 def summarize_text(text):
     sentences = text.split(". ")
     for i, sentence in enumerate(sentences):
@@ -20,8 +22,10 @@ def summarize_text(text):
             end = start + 3
             break
     abstract = ". ".join(sentences[start:end+1]) 
-    summarizer = pipeline("summarization", model="facebook/bart-large-cnn") 
-    summary = summarizer(abstract, max_length=30, min_length=30,
+
+    tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
+    summarizer = pipeline("summarization", model="facebook/bart-large-cnn", tokenizer=tokenizer) 
+    summary = summarizer(abstract, max_length=40, min_length=40,
                          do_sample=False)
     return summary[0]['summary_text']