New Delhi (India), 9th March 2023: Google has revealed additional details regarding the Unified Speech Model (USM). The USM is a system that has been referred to as a “critical first step” in achieving the company’s objectives. The USM is a system that is helping the company get closer to its objective of developing an artificial intelligence (AI) language model that supports 1,000 different languages in order to surpass ChatGPT.
Google revealed its USM model and aims to build a language model that supports 1,000 of the most widely spoken languages in the world in November of last year.
A family of cutting-edge speech models called USM has been described as having 2 billion parameters trained on 12 million hours of speech and 28 billion sentences of text, covering more than 300 languages.
Google said in their blog post, “USM, which is for use in YouTube (e.g., for closed captions), can perform automatic speech recognition (ASR) not only on widely spoken languages like English and Mandarin, but also on under-resourced languages like Amharic, Cebuano, Assamese, and Azerbaijani to name a few.”
