Interact with your documents using the power of GPT, 100% privately, no data leaks

Build realtime voice and video agents with Google's new Gemini 2.0 (API is free for now)

Large-scale pretrained models for goal-directed dialog

AgentSearch is a framework for powering search agents and enabling customizable local search.

Focus on prompting and generating

Experimental code: sound file preprocessing to optimize Whisper transcriptions without hallucinated texts

Code for ICASSP 2024 paper WhisperSeg: Positive Transfer of the Whisper Speech Transformer to Human and Animal Voice Activity Detection

Code and documentation to train Stanford's Alpaca models, and generate the data.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.