Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

请问该代码支持字幕上下文识别吗? #30

Open
larny opened this issue Jun 23, 2024 · 2 comments
Open

请问该代码支持字幕上下文识别吗? #30

larny opened this issue Jun 23, 2024 · 2 comments
Assignees
Labels
question Further information is requested

Comments

@larny
Copy link

larny commented Jun 23, 2024

开发者您好,

感谢您开发的库,非常有用。有两个问题想咨询下。

  1. 是否支持字幕的上下文读取?如果不按照逐行翻译,把整段输入到gpt4里,模型会根据上下文做参考,典型应用在于字幕中经常使用代词“它”、“这个”,如果逐行翻译可能无法识别之前输入到模型中的内容,导致翻译结果仍为“It“, ”This "。

  2. 是否支持输入词典(额外的promt语句),有的专有名词希望能对应翻译我设置的词典。

Regards,
Larny

@Cerlancism Cerlancism self-assigned this Jun 23, 2024
@Cerlancism Cerlancism added the question Further information is requested label Jun 23, 2024
@Cerlancism
Copy link
Owner

Cerlancism commented Jun 23, 2024

  1. 上下文读取默认是 100 行,前文历史默认史是 10
    • Web GUI 只用默认
    • CLI 可设置 --batch-sizes --history-prompt-length
  2. 这是 System Instruction, 默认是 Translate ${from} to ${to},
    • Web GUI 可设置 System Instruction
    • CLI 可设置 --system-instruction

@larny
Copy link
Author

larny commented Jun 25, 2024 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants