Update app.py

app.py

@@ -38,14 +38,14 @@ def clean_text(text: str) -> str:
     return text
 
 
-newline_to_space  = Replace(Regex(r'\s*\n\s*'), " ")
-join_hyphen_break = Replace(Regex(r'(\w+)[--]\s*\n\s*(\w+)'), r"\1\2")
+newline_to_space  = Replace(Regex(r"\s*\n\s*"), " ")
+join_hyphen_break = Replace(Regex(r"(\w+)-\s*\n\s*(\w+)"), r"\1\2")
 
 tokenizer.backend_tokenizer.normalizer = Sequence([
-    tokenizer.backend_tokenizer.normalizer,
-    join_hyphen_break,
-    newline_to_space,
-    Strip()
+        NFKC(),              
+        join_hyphen_break,
+        newline_to_space,
+        Strip()
 ])
 
 def classify_text(text):