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 suite: supports nearly 100 language inputs with a simultaneous delay of only 2 seconds

2024-02-28 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >

Share

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

CTOnews.com, December 4, Meta recently released the AI translation suite Seamless Communication, which consists of four AI models. Meta claims that the AI suite can "accurately reproduce the speaker's mood", achieve simultaneous interpretation with a delay of only 2 seconds, and support nearly 100 language input.

It is reported that Seamless Communication is the research result published by Meta to celebrate the 10th anniversary of the founding of its AI research organization "Fundamental AI Research".

According to Meta, the suite includes the "second generation SeamlessM4T model" for accelerating translation, the interpretation model "Seamless Expressive", and the simultaneous interpretation model "Seamless Streaming". With the integrated model "Seamless", CTOnews.com collates the relevant information as follows:

The SeamlessM4T model claims to be able to automatically associate possible later texts based on what users say during translation in order to speed up translation.

Seamless Expressive is an interpretation model, which claims to solve the problem that "the traditional AI translation can not grasp the user's intonation, pause and light word weight". It can preserve the user's mood, style, speaking speed, pause and rhythm while maintaining the translation quality, thus bringing more "emotional information" to the translated content.

Seamless Streaming is a simultaneous interpretation model, which focuses on speech and text translation with a 2-second delay, and supports interpretation (speech-to-speech translation), dictation translation (speech-to-text translation,S2TT) and automatic speech recognition (Automatic speech recognition, ASR).

On the other hand, the comprehensive model Seamless integrates the above three language models to facilitate the general scenario.

At present, Meta has posted sample videos on GitHub and HuggingFace, which can be viewed by interested friends.

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