added regex expression

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
+import re
 
 tokenizer = AutoTokenizer.from_pretrained("nebiyu29/fintunned-v2-roberta_GA")
 model = AutoModelForSequenceClassification.from_pretrained("nebiyu29/fintunned-v2-roberta_GA")
@@ -10,6 +11,8 @@ model = model.to(device)
 
 # Define a function to split a text into segments of 512 tokens
 def split_text(text):
+    #remove unnessary charachters
+    text=re.sub(r'[^a-zA-Z\s]','',text)
     # Tokenize the text
     tokens = tokenizer.tokenize(text)
     # Initialize an empty list for segments