-
An Introduction to Whisper Architecture with Subtitle Generator
Whisper is a multitask, multilingual model trained on 680,000 hours of diverse audio data. Its transformer-based architecture transcribes, translates, and identifies languages directly from raw audio—all in a single end-to-end pipeline.
-
Simple 3D Gaussian Splats from Unposed Images
NoPoSplat introduces a feed-forward network that directly predicts 3D Gaussian parameters within a canonical space from sparse, unposed multi-view images.
-
3D Gaussian Splatting
3D Gaussian splatting is a technique used in the field of real-time radiance field rendering.
