GitHub

VideoPrism: A Foundational Visual Encoder for Video Understanding

VideoPrism is a general-purpose video encoder designed to handle a wide spectrum of video understanding tasks, including classification, retrieval, localization, captioning, and question answering. It ...
IEEE

An Effective Mixture-Of-Experts Approach For Code-Switching Speech Recognition Leveraging ...

Abstract: With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the code-switching ...
IEEE

Code-Switching Speech Synthesis Based on Self-Supervised Learning and Domain Adaptive ...

Abstract: Recently, end-to-end speech synthesis models based on deep learning have made great progress in speech quality, and gradually replaced traditional speech synthesis methods into the ...
GitHub

Arduino library for AS5600 and AS5600L magnetic rotation meter.

AS5600 is a library for an AS5600 / AS5600L based magnetic rotation meter. More exact, it measures the angle (rotation w.r.t. reference) and not RPM. Multiple angle measurements allows one to ...