From f5b8d5dad2bb0ee5c8997a1b1536b9113a94a415 Mon Sep 17 00:00:00 2001 From: Yifan Yang <64255737+yfyeung@users.noreply.github.com> Date: Tue, 2 Apr 2024 15:49:03 +0800 Subject: [PATCH] Update preprocess_gigaspeech2.py --- egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py b/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py index 3477cc1e5..2989157c0 100755 --- a/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py +++ b/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py @@ -75,12 +75,12 @@ def normalize_text( text = re.sub(r"\u00B0", "องศา", text) # ° # Remove blank symbols - text = re.sub(r"\s", "", utt) + text = re.sub(r"\s", "", text) else: text = re.sub(r"\s+", " ", text).strip() - return utt + return text def preprocess_gigaspeech2(args):