From f284f1c2772223db4dfbddb67bda76188a9ff1a3 Mon Sep 17 00:00:00 2001
From: Srikar Bhargav Durgi <sdurgi17@gmail.com>
Date: Wed, 15 May 2024 15:00:57 +0530
Subject: [PATCH] fix typo in comment relating regex in encoder.py

---
 src/encoder.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/encoder.py b/src/encoder.py
index 5f52e723c..a40f75819 100644
--- a/src/encoder.py
+++ b/src/encoder.py
@@ -49,7 +49,7 @@ def __init__(self, encoder, bpe_merges, errors='replace'):
         self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
         self.cache = {}
 
-        # Should haved added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
+        # Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
         self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""")
 
     def bpe(self, token):