From 123cd9cb6d65e61d4e18225d2407bdcb07bd0856 Mon Sep 17 00:00:00 2001 From: jinzr Date: Fri, 8 Mar 2024 19:32:07 +0800 Subject: [PATCH] Update preprocess_mdcc.py --- egs/mdcc/ASR/local/preprocess_mdcc.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/egs/mdcc/ASR/local/preprocess_mdcc.py b/egs/mdcc/ASR/local/preprocess_mdcc.py index 2e2115de5..436bcad11 100755 --- a/egs/mdcc/ASR/local/preprocess_mdcc.py +++ b/egs/mdcc/ASR/local/preprocess_mdcc.py @@ -118,7 +118,7 @@ def get_word_segments(lines: List[str]) -> List[str]: def get_words(lines: List[str]) -> List[str]: words = set() for line in tqdm(lines, desc="Getting words"): - words.update(line.strip().split(" ")) + words.update(line.replace("\n", "").split(" ")) return list(words)