This article discusses a media repurpose tool that can record, scan objects, and transplant pictures from various platforms. It is capable of sharing dialogs and information across different platforms and streaming services. Using OCR technology to filter out textual information, the tool also finds new titles from danmaku or comments. The project is open-source and will receive regular tutorial updates.

Consider recording the media before real-time processing.

Scan the object via taobao streaming and make it dance.

Transplant lolita pictures to bilibili.

Share dialogs/info from soul/qq/wechat.

Repurpose a wide range of streaming platforms.

use ocr to filter out text info

find new title from danmaku or comments

我们都知道,视频主要由画面和音频组成。但还有一个元素同样包含了巨大的信息量 —— 字幕。结合现有的自然语言处理模型,我们便能实现对话抽取式的自动剪辑。PS: 软件图标是我妹妹Hannah设计滴~

项目开源地址:https://github.com/COLOR-SKY/DialogueExtractor

学业之余我会陆续更新工具教程。

Comments