← Back to Projects
Open Source

OmniVinci

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

Source: GitHub Pricing: Open Source
💻 View Code

About This Project

OmniVinci is an initiative to build a strong, open-source, omni-modal LLM. It introduces OmniAlignNet, Temporal Embedding Grouping, and Constrained Rotary Time for joint understanding across vision, audio, and language.

Tags

multimodal-llm omni-modal vision-audio-language

Reviews & Ratings

Share your experience

User Reviews (0)

No reviews yet. Be the first to share your experience!