Universal Speech Translator (UST) is the project to enable speech-to-speech translation with real-time, natural-sounding translations at near-human level quality. This code repository open sources our latest works for the mission, including code, model architecture design, data mining, and benchmark efforts.

Refactor, understand, and write code effortlessly using Cursor's AI source editor.

Imagic is a method for Text-Based Real Image editing with models like stable diffusion with just one image of a subject. The train_imagic.py script shows how to implement the training procedure and adapt it for stable diffusion.

Riku empowers you to build AI models without code. Use AI through integrations, API, or public share links. Accessible AI for everyone.

A comprehensive conversational AI platform to create and manage intelligent and contextual in-app voice assistants.

A modern investment research platform for everyone.

Official implementation of the paper Musika! Fast Infinite Waveform Music Generation, accepted to ISMIR 2022. This work was conducted as part of Marco Pasini's Master thesis at the Institute of Computational Perception at JKU Linz, with Jan Schlüter as supervisor.

Data Labeling with experts. With People For AI the best annotation tool and the annotation method will be select for you.

All-you-can-eat image object detection at a fixed monthly price.