From 0dd1d38c86a600d7a56e17fbf61dea9f41c48313 Mon Sep 17 00:00:00 2001
From: jmaple12 <93472187+jmaple12@users.noreply.github.com>
Date: Thu, 11 Apr 2024 22:18:38 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=94=B9pre=5Fseg=5Ftext=E4=B8=AD?=
 =?UTF-8?q?=E5=BC=80=E5=A4=B4=E4=BB=A5=E5=8F=8A=E5=AF=B9=E5=A4=9A=E4=B8=AA?=
 =?UTF-8?q?=E6=8D=A2=E8=A1=8C=E7=AC=A6=E7=9A=84=E6=9B=BF=E6=8D=A2?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

在text = text.strip("\n") 后面加入判断，防止text为空字符串。
使用正则式来替换原来将\n\n换为\n的式子
---
 GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py b/GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py
index 58b2678..f04a63d 100644
--- a/GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py
+++ b/GPT_SoVITS/TTS_infer_pack/TextPreprocessor.py
@@ -71,22 +71,24 @@ class TextPreprocessor:
 
     def pre_seg_text(self, text:str, lang:str, text_split_method:str):
         text = text.strip("\n")
-        if (text[0] not in splits and len(get_first(text)) < 4): 
-            text = "。" + text if lang != "en" else "." + text
+        #防止text成为空字符串
+        if text:
+            if (text[0] not in splits and len(get_first(text)) < 4): 
+                text = text + "。" if lang != "en" else text + "."
         print(i18n("实际输入的目标文本:"))
         print(text)
         
         seg_method = get_seg_method(text_split_method)
         text = seg_method(text)
         
-        while "\n\n" in text:
-            text = text.replace("\n\n", "\n")
+        # while "\n\n" in text:
+        #     text = text.replace("\n\n", "\n")
+        text = re.sub(r'\n+','\n', text)
 
         _texts = text.split("\n")
         _texts = merge_short_text_in_array(_texts, 5)
         texts = []
 
-        
         for text in _texts:
             # 解决输入目标文本的空行导致报错的问题
             if (len(text.strip()) == 0):
@@ -98,7 +100,7 @@ class TextPreprocessor:
                 texts.extend(split_big_text(text))
             else:
                 texts.append(text)
-            
+        
         print(i18n("实际输入的目标文本(切句后):"))
         print(texts)
         return texts