AI Agent Skills

Speech recognition module for Python, supporting several engines and APIs, online and offline.

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

3D ResNets for Action Recognition (CVPR 2018)

Open-Source Large Vocabulary Continuous Speech Recognition Engine

:unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures

Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition