diff --git a/minbpe/regex.py b/minbpe/regex.py
index 0c282571..9ed78e43 100644
--- a/minbpe/regex.py
+++ b/minbpe/regex.py
@@ -146,7 +146,7 @@ def encode(self, text, allowed_special="none_raise"):
             return self.encode_ordinary(text)
         # otherwise, we have to be careful with potential special tokens in text
         # we handle special tokens by splitting the text
-        # based on the occurence of any exact match with any of the special tokens
+        # based on the occurrence of any exact match with any of the special tokens
         # we can use re.split for this. note that surrounding the pattern with ()
         # makes it into a capturing group, so the special tokens will be included
         special_pattern = "(" + "|".join(re.escape(k) for k in special) + ")"