安装 Steam
登录
|
语言
繁體中文(繁体中文)
日本語(日语)
한국어(韩语)
ไทย(泰语)
български(保加利亚语)
Čeština(捷克语)
Dansk(丹麦语)
Deutsch(德语)
English(英语)
Español-España(西班牙语 - 西班牙)
Español - Latinoamérica(西班牙语 - 拉丁美洲)
Ελληνικά(希腊语)
Français(法语)
Italiano(意大利语)
Bahasa Indonesia(印度尼西亚语)
Magyar(匈牙利语)
Nederlands(荷兰语)
Norsk(挪威语)
Polski(波兰语)
Português(葡萄牙语 - 葡萄牙)
Português-Brasil(葡萄牙语 - 巴西)
Română(罗马尼亚语)
Русский(俄语)
Suomi(芬兰语)
Svenska(瑞典语)
Türkçe(土耳其语)
Tiếng Việt(越南语)
Українська(乌克兰语)
报告翻译问题






Length of voice must be shorter than the original voice segment. Otherwise, the voice will be sliced. That's why I adopted a simple algorithm to accerlate the voice speed to some extend. Conseqently, some of the voice is fast, some are lack of interval.
In term of translated contents, they are generated by my AI model. I don't have sufficient confidence in its accuracy. But I have no time to translate and correct Japanese version manually. In future work, I will use LLM like ChatGPT or ChatRWKV to solve those problems.
I am majored at AI & CS, everything is done automatically once the project is well established. The only thing to prevent me from publishing MOD is the god damm ** L4D2 authoring tools. lol