Meta’s AI Translations Inference

In this talk we will show how we implemented a media processing pipeline to perform (autodub / lipsync) media inference at Meta scale.

We will focus on the challenges we faced from a media processing / scaling point of view, such as: inference latency and scheduling, voice isolation, media timing/alignment, alternate tracks delivery, instrumentation, model evaluation, etc.

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy