Meta Open Sources AI Massively Multilingual Speech Project

Meta has open sourced its Massively Multilingual Speech (MMS) project, which can identify more than 4,000 spoken languages. According to the announcement, the MMS models also expand text-to-speech capabilities “from around 100 languages to more than 1,100.”

“We’re open sourcing our models and code so that others in the research community can build on our work and help preserve the world’s languages and bring the world closer together,” the company says.

Meta recently made other AI-related announcements, including revealing that it has built an AI supercomputer for training large language models, such as the LLaMA project.

Looking for a job?
Sign up for job alerts and check out the latest listings at Open Source JobHub.

FOSSlife Newsetter




Contact FOSSlife to learn about partnership and sponsorship opportunities.