From a88a1d9938eec790aa7333fe6c3d33e5e2067256 Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期二, 25 四月 2023 16:50:04 +0800
Subject: [PATCH] update text tokenize
---
funasr/datasets/preprocessor.py | 11 +++++++++--
1 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/preprocessor.py b/funasr/datasets/preprocessor.py
index 20a3831..758c750 100644
--- a/funasr/datasets/preprocessor.py
+++ b/funasr/datasets/preprocessor.py
@@ -44,15 +44,22 @@
i += len(longest_word)
return word_list
-
def seg_tokenize(txt, seg_dict):
+ pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
out_txt = ""
for word in txt:
word = word.lower()
if word in seg_dict:
out_txt += seg_dict[word] + " "
else:
- out_txt += "<unk>" + " "
+ if pattern.match(word):
+ for char in word:
+ if char in seg_dict:
+ out_txt += seg_dict[char] + " "
+ else:
+ out_txt += "<unk>" + " "
+ else:
+ out_txt += "<unk>" + " "
return out_txt.strip().split()
def seg_tokenize_wo_pattern(txt, seg_dict):
--
Gitblit v1.9.1