In November final yr, the corporate introduced its plans to create a language mannequin supporting 1,000 of the world’s most-spoken languages whereas additionally revealing its USM mannequin.
The tech big describes USM as a household of state-of-the-art speech fashions with 2 billion parameters skilled on 12 million hours of speech and 28 billion sentences of textual content, 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 mentioned in a blogpost.
Google at present claims that USM helps over 100 languages and can function the “foundation” for a a lot bigger system.
Discover the tales of your curiosity
Meanwhile, Google is anticipated to introduce a number of AI options for its merchandise within the close to future, and amongst them, Gboard for Android is working to combine the Imagen text-to-image generator.
Source: economictimes.indiatimes.com