From 7aee2a6a718e9398315533d171625ee015205a6f Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期五, 17 三月 2023 15:14:18 +0800
Subject: [PATCH] update
---
funasr/datasets/large_datasets/utils/tokenize.py | 10 +++-------
1 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index caeb426..a016e4e 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -18,15 +18,11 @@
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 tokenize(data,
--
Gitblit v1.9.1