From 4dc3a1b011e1e72eb737417b8e0e0bec7a7e3a6e Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期二, 21 三月 2023 15:12:21 +0800
Subject: [PATCH] resolve conflict
---
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