From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn

---
 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