Listen to the Podcast:
Google has released new details about the Universal Speech Model (USM), a system the company describes as an “essential first step” in achieving its goals.
The company is now getting closer to its goal of building an AI language model that supports 1000 languages to beat ChatGPT.
In November last year, the company unveiled its USM model and its aspirations to build a language model that supports 1,000 of the world’s most widely spoken languages.
The tech giant describes USM as a collection of cutting-edge speech models with 2 billion parameters trained on 12 million hours of speech and 28 billion sentences of text in more than 300 languages.
“USM, which is designed to be used on YouTube (for example, for subtitles), can perform Automatic Speech Recognition (ASR) not only on widely spoken languages like English and Mandarin, but also on languages that aren’t as common. like Japanese and Korean. in under-resourced languages like Amharic, Cebuano, Assamese, and Azerbaijani, to name a few,” Google wrote in a blog post.
Google says that USM works with more than 100 languages and will be the “base” for a much larger system.
Meanwhile, Google is scheduled to roll out a host of AI capabilities for its products in the coming months, including Gboard for Android, which plans to integrate the Image text-to-image generator.
Subscribe to our latest newsletter
To read our exclusive content, sign up now. $5/month, $50/year
Categories: Technology
Source: vtt.edu.vn