←
Back to Open Source
🐙 GitHub Detail
V
KastanDay/video-pretrained-transformer
By KastanDay
Multi-model video-to-text by combining embeddings from Flan-T5 + CLIP + Whisper + SceneGraph. The 'backbone LLM' is pre-trained from scratch on YouTube (YT-1B dataset).
GitHub
Jupyter Notebook
MIT License
Updated 13 Feb 2026
Live Snapshot
⭐
Stars
54
🍴
Forks
11
📄
License
MIT License
🧩
Type
Jupyter Notebook
📘
About this open-source project
Live information fetched from GitHub.
Multi-model video-to-text by combining embeddings from Flan-T5 + CLIP + Whisper + SceneGraph. The 'backbone LLM' is pre-trained from scratch on YouTube (YT-1B dataset).
🌿
Default Branch
main
🐞
Open Issues
0
👀
Watchers
54