Weibo transcribe
微博视频 → 下载 → 转录 → 存为 Markdown。 支持微博视频链接,无需登录。From its SKILL.md
npx -y skills add chubbyguan/chubbyskills --skill weibo-transcribeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- runs commandsInstructs the agent to run 5 commands, including `pip install funasr modelscope torch torchaudio` and 4 more.
- fetches URLsInstructs the agent to fetch 2 URLs, including https://weibo.com/xxxxx and 1 more.
SKILL.md
1.4 KB, 365 tokens by cl100k_base, as published. Nobody here has run it
微博视频转录 Skill
将微博视频下载音频,用 SenseVoice-Small 转录为文字,存为 Markdown 文件。
环境要求
pip install funasr modelscope torch torchaudio
brew install ffmpeg yt-dlp # macOS
使用方法
python scripts/transcribe.py "https://weibo.com/xxxxx"
python scripts/transcribe.py "https://m.weibo.cn/xxxxx"
流程
- yt-dlp 下载微博视频音频
- SenseVoice-Small 转录
- 生成带 frontmatter 的 Markdown
已知限制
- 部分微博视频可能需要登录才能访问
- SenseVoice-Small 主要针对中文优化
致谢
- yt-dlp/yt-dlp — 视频下载工具
- FunAudioLLM/SenseVoice — 语音识别模型
⚖️ 合规声明
仅供个人学习与研究使用。请遵守目标平台的服务条款(ToS)与 robots 规则,控制请求频率,不要用于批量抓取、商用爬取或侵犯他人权益的场景。下载内容的版权归原作者所有。
What ships with it: 2 files
5.9 KB alongside SKILL.md, 1 of them executable
scripts/
- transcribe.pyruns5.9 KB
- requirements.txt64 B