From b0887f17678e0e5c4bd895e36695b242f2f1aee8 Mon Sep 17 00:00:00 2001
From: mengzhe.cmz <mengzhe.cmz@alibaba-inc.com>
Date: 星期四, 23 三月 2023 19:59:28 +0800
Subject: [PATCH] Merge branch 'dev_gzf' of github.com:alibaba-damo-academy/FunASR into dev_gzf
---
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