Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255)

* ruff check --fix

* ruff format --line-length 120 --target-version py39

* Change the link for G2PW Model

* update pytorch version and colab

GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py

@@ -1,41 +1,57 @@
-
-
-
-
 import re
 from typing import Callable
 
-punctuation = set(['!', '?', '…', ',', '.', '-'," "])
+punctuation = set(["!", "?", "…", ",", ".", "-", " "])
 METHODS = dict()
 
-def get_method(name:str)->Callable:
+
+def get_method(name: str) -> Callable:
     method = METHODS.get(name, None)
     if method is None:
         raise ValueError(f"Method {name} not found")
     return method
 
-def get_method_names()->list:
+
+def get_method_names() -> list:
     return list(METHODS.keys())
 
+
 def register_method(name):
     def decorator(func):
         METHODS[name] = func
         return func
+
     return decorator
 
-splits = {"，", "。", "？", "！", ",", ".", "?", "!", "~", ":", "：", "—", "…", }
+
+splits = {
+    "，",
+    "。",
+    "？",
+    "！",
+    ",",
+    ".",
+    "?",
+    "!",
+    "~",
+    ":",
+    "：",
+    "—",
+    "…",
+}
+
 
 def split_big_text(text, max_len=510):
     # 定义全角和半角标点符号
     punctuation = "".join(splits)
 
     # 切割文本
-    segments = re.split('([' + punctuation + '])', text)
-    
+    segments = re.split("([" + punctuation + "])", text)
+
     # 初始化结果列表和当前片段
     result = []
-    current_segment = ''
-    
+    current_segment = ""
+
     for segment in segments:
         # 如果当前片段加上新的片段长度超过max_len，就将当前片段加入结果列表，并重置当前片段
         if len(current_segment + segment) > max_len:
@@ -43,13 +59,12 @@ def split_big_text(text, max_len=510):
             current_segment = segment
         else:
             current_segment += segment
-    
+
     # 将最后一个片段加入结果列表
     if current_segment:
         result.append(current_segment)
-    
-    return result
 
+    return result
 
 
 def split(todo_text):
@@ -90,7 +105,7 @@ def cut1(inp):
     if len(split_idx) > 1:
         opts = []
         for idx in range(len(split_idx) - 1):
-            opts.append("".join(inps[split_idx[idx]: split_idx[idx + 1]]))
+            opts.append("".join(inps[split_idx[idx] : split_idx[idx + 1]]))
     else:
         opts = [inp]
     opts = [item for item in opts if not set(item).issubset(punctuation)]
@@ -123,6 +138,7 @@ def cut2(inp):
     opts = [item for item in opts if not set(item).issubset(punctuation)]
     return "\n".join(opts)
 
+
 # 按中文句号。切
 @register_method("cut3")
 def cut3(inp):
@@ -131,26 +147,28 @@ def cut3(inp):
     opts = [item for item in opts if not set(item).issubset(punctuation)]
     return "\n".join(opts)
 
-#按英文句号.切
+
+# 按英文句号.切
 @register_method("cut4")
 def cut4(inp):
     inp = inp.strip("\n")
-    opts = re.split(r'(?<!\d)\.(?!\d)', inp.strip("."))
+    opts = re.split(r"(?<!\d)\.(?!\d)", inp.strip("."))
     opts = [item for item in opts if not set(item).issubset(punctuation)]
     return "\n".join(opts)
 
+
 # 按标点符号切
 # contributed by https://github.com/AI-Hobbyist/GPT-SoVITS/blob/main/GPT_SoVITS/inference_webui.py
 @register_method("cut5")
 def cut5(inp):
     inp = inp.strip("\n")
-    punds = {',', '.', ';', '?', '!', '、', '，', '。', '？', '！', ';', '：', '…'}
+    punds = {",", ".", ";", "?", "!", "、", "，", "。", "？", "！", ";", "：", "…"}
     mergeitems = []
     items = []
 
     for i, char in enumerate(inp):
         if char in punds:
-            if char == '.' and i > 0 and i < len(inp) - 1 and inp[i - 1].isdigit() and inp[i + 1].isdigit():
+            if char == "." and i > 0 and i < len(inp) - 1 and inp[i - 1].isdigit() and inp[i + 1].isdigit():
                 items.append(char)
             else:
                 items.append(char)
@@ -166,8 +184,6 @@ def cut5(inp):
     return "\n".join(opt)
 
 
-
-if __name__ == '__main__':
+if __name__ == "__main__":
     method = get_method("cut5")
     print(method("你好，我是小明。你好，我是小红。你好，我是小刚。你好，我是小张。"))
-