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

太长的视频无法总结完整,建议加入自动分段总结 #16

Open
SlatitudeChou opened this issue Mar 17, 2023 · 3 comments
Open
Labels
discussion enhancement New feature or request

Comments

@SlatitudeChou
Copy link

Is your feature request related to a problem? Please describe.
新功能是否与解决某个问题相关, 请描述
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Describe the solution you'd like
你期望的新功能实现方案
A clear and concise description of what you want to happen.

Additional context
其他
Add any other context or screenshots about the feature request here.

@josStorer josStorer added enhancement New feature or request discussion labels Mar 17, 2023
@josStorer
Copy link
Owner

目前长视频的总结模式是, 保留开头结尾, 对中间部分按比例裁切, 保证在一定token范围内, 以期望保留视频整体大意
核心逻辑见: https://github.com/josStorer/chatGPTBox/blob/master/src/utils/crop-text.mjs

分段总结是可行的, 但会导致某些长视频消耗大量token, 并且每个片段将使用独立上下文, 导致难以与其他片段关联, 目前这个功能优先级不高, 并且不一定会支持, 如果有好的想法可以在这个issue下讨论

@DIYer22
Copy link

DIYer22 commented Mar 21, 2023

怪不得, 没法基于视频问答. 我觉得可以设置一个选项, 节约模式和性能模式, 或者(概览/完全), 放在视频问答窗口的按钮, 让用户自己选择. 或者在设置界面新增单个视频最长 token 长度的设置, 根据设置长度来截取字幕

对于有 API key 用户, 额度多得消耗不完, 想要性能模式.

@ssyzyg
Copy link

ssyzyg commented Mar 21, 2023

对于长视频,一种简单的做法可以是拆分视频/文本长度,比如每5分钟做摘要,然后对各个摘要汇总做二次摘要,实测下来也可以达到要求,而且也可输出分段摘要。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
discussion enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

4 participants