mirror of
https://github.com/RVC-Boss/GPT-SoVITS.git
synced 2025-04-06 03:57:44 +08:00
ec7647e08d
* 为fast_inference分支适配新的WebAPI * modified: api_v2.py * 修改文档细节 * modified: api_v2.py * 优化了代码逻辑，提升健壮性 * 修改文档细节 * 修改文档细节 * 优化代码逻辑 * 修改注释细节
158 lines
4.2 KiB
Python
158 lines
4.2 KiB
Python
|
||
|
||
|
||
|
||
import re
|
||
from typing import Callable
|
||
from tools.i18n.i18n import I18nAuto
|
||
|
||
i18n = I18nAuto()
|
||
|
||
METHODS = dict()
|
||
|
||
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:
|
||
return list(METHODS.keys())
|
||
|
||
def register_method(name):
|
||
def decorator(func):
|
||
METHODS[name] = func
|
||
return func
|
||
return decorator
|
||
|
||
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)
|
||
|
||
# 初始化结果列表和当前片段
|
||
result = []
|
||
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:
|
||
result.append(current_segment)
|
||
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
|
||
|
||
|
||
|
||
def split(todo_text):
|
||
todo_text = todo_text.replace("……", "。").replace("——", "，")
|
||
if todo_text[-1] not in splits:
|
||
todo_text += "。"
|
||
i_split_head = i_split_tail = 0
|
||
len_text = len(todo_text)
|
||
todo_texts = []
|
||
while 1:
|
||
if i_split_head >= len_text:
|
||
break # 结尾一定有标点，所以直接跳出即可，最后一段在上次已加入
|
||
if todo_text[i_split_head] in splits:
|
||
i_split_head += 1
|
||
todo_texts.append(todo_text[i_split_tail:i_split_head])
|
||
i_split_tail = i_split_head
|
||
else:
|
||
i_split_head += 1
|
||
return todo_texts
|
||
|
||
|
||
# 不切
|
||
@register_method("cut0")
|
||
def cut0(inp):
|
||
return inp
|
||
|
||
|
||
# 凑四句一切
|
||
@register_method("cut1")
|
||
def cut1(inp):
|
||
inp = inp.strip("\n")
|
||
inps = split(inp)
|
||
split_idx = list(range(0, len(inps), 4))
|
||
# split_idx[-1] = None
|
||
split_idx.append(None)
|
||
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]]))
|
||
else:
|
||
opts = [inp]
|
||
return "\n".join(opts)
|
||
|
||
# 凑50字一切
|
||
@register_method("cut2")
|
||
def cut2(inp):
|
||
inp = inp.strip("\n")
|
||
inps = split(inp)
|
||
if len(inps) < 2:
|
||
return inp
|
||
opts = []
|
||
summ = 0
|
||
tmp_str = ""
|
||
for i in range(len(inps)):
|
||
summ += len(inps[i])
|
||
tmp_str += inps[i]
|
||
if summ > 50:
|
||
summ = 0
|
||
opts.append(tmp_str)
|
||
tmp_str = ""
|
||
if tmp_str != "":
|
||
opts.append(tmp_str)
|
||
# print(opts)
|
||
if len(opts) > 1 and len(opts[-1]) < 50: ##如果最后一个太短了，和前一个合一起
|
||
opts[-2] = opts[-2] + opts[-1]
|
||
opts = opts[:-1]
|
||
return "\n".join(opts)
|
||
|
||
# 按中文句号。切
|
||
@register_method("cut3")
|
||
def cut3(inp):
|
||
inp = inp.strip("\n")
|
||
return "\n".join(["%s" % item for item in inp.strip("。").split("。")])
|
||
|
||
#按英文句号.切
|
||
@register_method("cut4")
|
||
def cut4(inp):
|
||
inp = inp.strip("\n")
|
||
return "\n".join(["%s" % item for item in inp.strip(".").split(".")])
|
||
|
||
# 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):
|
||
# if not re.search(r'[^\w\s]', inp[-1]):
|
||
# inp += '。'
|
||
inp = inp.strip("\n")
|
||
# punds = r'[,.;?!、，。？！;：…]'
|
||
punds = r'[,.;?!、，。？！；：:…]'
|
||
items = re.split(f'({punds})', inp)
|
||
mergeitems = ["".join(group) for group in zip(items[::2], items[1::2])]
|
||
# 在句子不存在符号或句尾无符号的时候保证文本完整
|
||
if len(items)%2 == 1:
|
||
mergeitems.append(items[-1])
|
||
opt = "\n".join(mergeitems)
|
||
return opt
|
||
|
||
|
||
|
||
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。"))
|
||
|