From abafc690e4cd7c726c30432c4eb8b0ebf95148a5 Mon Sep 17 00:00:00 2001
From: kobenaxie <572745565@qq.com>
Date: Tue, 25 Jul 2023 17:24:57 +0800
Subject: [PATCH] Update preprocess_commonvoice.py to fix text normalization
 bug.

---
 egs/commonvoice/ASR/local/preprocess_commonvoice.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/egs/commonvoice/ASR/local/preprocess_commonvoice.py b/egs/commonvoice/ASR/local/preprocess_commonvoice.py
index c5ec14502..e60459765 100755
--- a/egs/commonvoice/ASR/local/preprocess_commonvoice.py
+++ b/egs/commonvoice/ASR/local/preprocess_commonvoice.py
@@ -45,7 +45,7 @@ def get_args():
 
 def normalize_text(utt: str) -> str:
     utt = re.sub(r"[{0}]+".format("-"), " ", utt)
-    return re.sub(r"[^a-zA-Z\s]", "", utt).upper()
+    return re.sub(r"[^a-zA-Z\s']", "", utt).upper()
 
 
 def preprocess_commonvoice(