GitHub repo leaderboard by stars, growth rate and activity.
A cross-platform video structuring (video analysis) framework based on CV models & mLLM.
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API,使用本地运行的Whisper模型进行推理,并支持多GPU并发,针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫,可实现来自多个社交平台的无缝媒体处理,为媒体内容数据自动化处理提供了强大且可扩展的解决方案。
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | A cross-platform video structuring (video analysis) framework based on CV models & mLLM. | C++ | 2,944 | last pushed 7 months ago | |
| 2 | Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT. | Python | 2,129 | last pushed 2 weeks ago | |
| 3 | ⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API,使用本地运行的Whisper模型进行推理,并支持多GPU并发,针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫,可实现来自多个社交平台的无缝媒体处理,为媒体内容数据自动化处理提供了强大且可扩展的解决方案。 | Python | 471 | last pushed 1 year ago |
All · 11,474