Founding Machine Learning Intern

Designed a Generative AI pipeline for automated video transformation, visual face dubbing, and voice conversion.
Created a system to detect and extract the landmarks from the face of a particular individual in a video.
Implemented a facial landmark detection system to drive a GAN-based FreeVC model for voice cloning and a DINet model for visual dubbing.
Improved inference performance by 17% and successfully integrated the pipeline into the company’s production.