Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account

Shulou

Meta launches "seamless communication" AI translation model, which brings a more natural cross-language dialogue experience.

2024-07-24 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >

Share

Shulou(Shulou.com)12/24 Report--

CTOnews.com, December 4 (Xinhua)-- in August this year, Meta launched its multimodal artificial intelligence translation model, SeamlessM4T, which supports text in nearly 100 languages and speech in 36 languages. Now the model updates the "v2" architecture, which Meta calls the "Seamless Communication (seamless communication)" model, which makes dialogue translation more natural and expressive.

The first of the two new features is "SeamlessExpressive", which, as the name suggests, transfers your tone to the translated voice, including tone, volume, emotional color (excitement, sadness or whispering), speed and pause. Considering that the translated voice generally sounds mechanical, this breakthrough is worth looking forward to, and is of great help both in our daily life and in the production of content. Currently, the languages it supports include English, Spanish, German, French, Italian, and Chinese, but at the time of this writing, the presentation page lacked Italian and Chinese.

The second function is "SeamlessStreaming", which can start the translation while the speaker is still speaking, so that others can hear the translation more quickly. Although there is still a short delay of less than two seconds, at least you don't have to wait until the other person finishes a sentence. According to Meta, the biggest challenge is that different languages have different sentence structures, so they must develop a special algorithm to study part of the audio input to determine whether there is enough context to start generating translation output or whether to continue to listen.

CTOnews.com notes that Meta has not yet revealed when the new features will be available to the public, but can expect Meta to integrate them into its smart glasses in the future to make them more practical.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information

Wechat

© 2024 shulou.com SLNews company. All rights reserved.

12
Report