Hugging Face's logo

Ytgetahun
/
visual-narrator-llm

Image-to-Text
English
video-to-text
vision-language-model
real-time
accessibility
video-narration
cinematic-description
Model card Files
xet
Community
visual-narrator-llm / create_spatial_intensive_dataset.py

Commit History

feat: Visual Narrator 3B - Clean repository with professional benchmarks
d6e97b5

Ytgetahun commited on