From 7d22fef6f246d4ea9ab4621d2364f227174e21aa Mon Sep 17 00:00:00 2001 From: jinzr Date: Fri, 8 Mar 2024 19:25:13 +0800 Subject: [PATCH] Update preprocess_mdcc.py --- egs/mdcc/ASR/local/preprocess_mdcc.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/egs/mdcc/ASR/local/preprocess_mdcc.py b/egs/mdcc/ASR/local/preprocess_mdcc.py index f068425e7..86efd1f57 100755 --- a/egs/mdcc/ASR/local/preprocess_mdcc.py +++ b/egs/mdcc/ASR/local/preprocess_mdcc.py @@ -92,6 +92,8 @@ def get_word_segments(lines: List[str]) -> List[str]: if len(line.strip().split(" ")) > 1: segments = [] for segment in line.strip().split(" "): + if segment.strip() == "": + continue try: if not is_cjk(segment[0]): # en segment segments.append(segment)