From 835369d6315e96c1820326ed11ea4b999793720f Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期六, 13 一月 2024 22:42:18 +0800
Subject: [PATCH] funasr1.0 fix punc model

---
 funasr/models/ct_transformer/utils.py |  115 +++++++++++++++++++++++++++++++++++++++++++++++----------
 1 files changed, 95 insertions(+), 20 deletions(-)

diff --git a/funasr/models/ct_transformer/utils.py b/funasr/models/ct_transformer/utils.py
index a4a00e0..917f2e0 100644
--- a/funasr/models/ct_transformer/utils.py
+++ b/funasr/models/ct_transformer/utils.py
@@ -1,4 +1,4 @@
-
+import re
 
 def split_to_mini_sentence(words: list, word_limit: int = 20):
     assert word_limit > 1
@@ -14,23 +14,98 @@
     return sentences
 
 
-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
+# def split_words(text: str, **kwargs):
+#     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_words(text: str, jieba_usr_dict=None, **kwargs):
+    if jieba_usr_dict:
+        input_list = text.split()
+        token_list_all = []
+        langauge_list = []
+        token_list_tmp = []
+        language_flag = None
+        for token in input_list:
+            if isEnglish(token) and language_flag == 'Chinese':
+                token_list_all.append(token_list_tmp)
+                langauge_list.append('Chinese')
+                token_list_tmp = []
+            elif not isEnglish(token) and language_flag == 'English':
+                token_list_all.append(token_list_tmp)
+                langauge_list.append('English')
+                token_list_tmp = []
+
+            token_list_tmp.append(token)
+
+            if isEnglish(token):
+                language_flag = 'English'
             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
+                language_flag = 'Chinese'
+
+        if token_list_tmp:
+            token_list_all.append(token_list_tmp)
+            langauge_list.append(language_flag)
+
+        result_list = []
+        for token_list_tmp, language_flag in zip(token_list_all, langauge_list):
+            if language_flag == 'English':
+                result_list.extend(token_list_tmp)
+            else:
+                seg_list = jieba_usr_dict.cut(join_chinese_and_english(token_list_tmp), HMM=False)
+                result_list.extend(seg_list)
+
+        return result_list
+
+    else:
+        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 isEnglish(text:str):
+    if re.search('^[a-zA-Z\']+$', text):
+        return True
+    else:
+        return False
+
+def join_chinese_and_english(input_list):
+    line = ''
+    for token in input_list:
+        if isEnglish(token):
+            line = line + ' ' + token
+        else:
+            line = line + token
+
+    line = line.strip()
+    return line

--
Gitblit v1.9.1