From fab0da6ab7ceb3885b7e12287d2d2162e1c5409a Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期五, 17 三月 2023 15:09:41 +0800
Subject: [PATCH] update
---
funasr/datasets/preprocessor.py | 10 +++-------
1 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/funasr/datasets/preprocessor.py b/funasr/datasets/preprocessor.py
index 20a3791..98cca1d 100644
--- a/funasr/datasets/preprocessor.py
+++ b/funasr/datasets/preprocessor.py
@@ -47,15 +47,11 @@
def seg_tokenize(txt, seg_dict):
out_txt = ""
- pattern = re.compile(r"([\u4E00-\u9FA5A-Za-z0-9])")
for word in txt:
- if pattern.match(word):
- if word in seg_dict:
- out_txt += seg_dict[word] + " "
- else:
- out_txt += "<unk>" + " "
+ if word in seg_dict:
+ out_txt += seg_dict[word] + " "
else:
- continue
+ out_txt += "<unk>" + " "
return out_txt.strip().split()
def seg_tokenize_wo_pattern(txt, seg_dict):
--
Gitblit v1.9.1