From 8706e767affc6bdc8cb7a67ca3a20a62779ff048 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期三, 17 五月 2023 15:45:46 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into main

---
 funasr/datasets/preprocessor.py |   13 ++++++++++---
 1 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/funasr/datasets/preprocessor.py b/funasr/datasets/preprocessor.py
index 1adca05..758c750 100644
--- a/funasr/datasets/preprocessor.py
+++ b/funasr/datasets/preprocessor.py
@@ -44,14 +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):
@@ -359,7 +367,6 @@
             if self.split_with_space:
                 tokens = text.strip().split(" ")
                 if self.seg_dict is not None:
-                    tokens = forward_segment("".join(tokens), self.seg_dict)
                     tokens = seg_tokenize(tokens, self.seg_dict)
             else:
                 tokens = self.tokenizer.text2tokens(text)

--
Gitblit v1.9.1