Google has shared more information about the Universal Speech Model (USM). The system, which the company describes as an important first step in realizing its goal, is now nearing its goal of creating an AI voice model that can handle 1,000 different voice models. Languages ​​supported to beat ChatGPT.

Last November, the company announced plans to develop language models to support the 1,000 most widely spoken languages ​​in the world, and also announced the USM model.

Also read: New Regulations Bring Virtual Assets Under Money Laundering Laws

Google describes USM as a family of state-of-the-art language models with 2 billion parameters, trained on 12 million hours of speech and 28 billion sentences in 300 languages.

“USM intended for use on YouTube (such as subtitles) includes widely spoken languages ​​such as English and Mandarin, as well as Amharic, Cebuano, Assamese, and Azerbaijan, to name a few ‘, Google said in a blog post.

Google now claims that USM supports over 100 languages ​​and serves as the base for larger systems.

Meanwhile, Google plans to roll out various AI features to its products in the near future, among others Gboard for Android is working on integrating the text-to-image generator Imagen.

Also read: SoftBank’s Masayoshi Son Attends OYO Founder Ritesh Agarwal’s Wedding