优化日英/中英混合推理分词逻辑

示例

【1pass】（现在版本）
['我是一名粉刷匠，粉刷本领强，', 'I am a painter with strong painting skills', '，', 'A.B.C.D.A', '_', 'B', '—', 'C', '……', 'D.']
['zh', 'en', 'zh', 'en', 'zh', 'en', 'zh', 'en', 'zh', 'en']
【2pass】
['我是一名粉刷匠，粉刷本领强，', 'I am a painter with strong painting skills，', 'A.B.C.D.A_', 'B—', 'C……', 'D.']
['zh', 'en', 'en', 'en', 'en', 'en']
【result】
['我是一名粉刷匠，粉刷本领强，', 'I am a painter with strong painting skills，A.B.C.D.A_B—C……D.']
['zh', 'en']

GPT_SoVITS/inference_webui.py

@@ -215,6 +215,21 @@ def splite_en_inf(sentence, language):
     if pos < len(sentence):
         textlist.append(sentence[pos:])
         langlist.append(language)
+    # Merge punctuation into previous word
+    for i in range(len(textlist)-1, 0, -1):
+        if re.match(r'^[\W_]+$', textlist[i]):
+            textlist[i-1] += textlist[i]
+            del textlist[i]
+            del langlist[i]
+    # Merge consecutive words with the same language tag
+    i = 0
+    while i < len(langlist) - 1:
+        if langlist[i] == langlist[i+1]:
+            textlist[i] += textlist[i+1]
+            del textlist[i+1]
+            del langlist[i+1]
+        else:
+            i += 1
 
     return textlist, langlist