San Francisco, March 7,2023: Google has shared more information about the Universal Speech Model (USM), a system that the company describes as a “critical first step” in realising its goals, which is now moving closer toward its goal of building an AI language model that supports 1,000 different languages to beat ChatGPT.
In November last year, the company announced its plans to create a language model supporting 1,000 of the world’s most-spoken languages while also revealing its USM model.
The tech giant describes USM as a family of state-of-the-art speech models with 2 billion parameters trained on 12 million hours of speech and 28 billion sentences of text, spanning 300+ languages.
“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,” Google said in a blogpost.
Google currently claims that USM supports over 100 languages and will serve as the “foundation” for a much larger system.
Meanwhile, Google is expected to introduce a host of AI features for its products in the near future, and among them, Gboard for Android is working to integrate the Imagen text-to-image generator.
