From 80e6c258cf89b5f11f4e52a4cc5a9cf2e95aa7be Mon Sep 17 00:00:00 2001
From: Yuekai Zhang <zhangyuekai@foxmail.com>
Date: 星期一, 06 三月 2023 16:48:02 +0800
Subject: [PATCH] update token list

---
 funasr/punctuation/text_preprocessor.py |   21 ---------------------
 1 files changed, 0 insertions(+), 21 deletions(-)

diff --git a/funasr/punctuation/text_preprocessor.py b/funasr/punctuation/text_preprocessor.py
index 3d2c19e..c9c4bac 100644
--- a/funasr/punctuation/text_preprocessor.py
+++ b/funasr/punctuation/text_preprocessor.py
@@ -1,24 +1,3 @@
-def split_words(text: str):
-    words = []
-    segs = text.split()
-    for seg in segs:
-        # There is no space in seg.
-        current_word = ""
-        for c in seg:
-            if len(c.encode()) == 1:
-                # This is an ASCII char.
-                current_word += c
-            else:
-                # This is a Chinese char.
-                if len(current_word) > 0:
-                    words.append(current_word)
-                    current_word = ""
-                words.append(c)
-        if len(current_word) > 0:
-            words.append(current_word)
-    return words
-
-
 def split_to_mini_sentence(words: list, word_limit: int = 20):
     assert word_limit > 1
     if len(words) <= word_limit:

--
Gitblit v1.9.1