Shulou(Shulou.com)11/24 Report--

CTOnews.com, August 22 (Xinhua) the Electronic Engineering Department of Tsinghua University recently joined hands with the byte-beating Volcano Voice team to launch an open source big language model, SALMONN.

After querying the GitHub page CTOnews.com of the ▲ image source SALMONN, we know that the SALMONN model supports voice, audio and music input, it can perceive and understand different types of audio content input, and has the functions of multilingual speech recognition, translation and speech reasoning.

The official model parsing chart released by ▲ officially said that SALMONN supports voice, audio and music input, it can perceive and understand different types of audio content input, and has the functions of multilingual speech recognition and translation as well as speech reasoning.

The official Demo page of ▲ image source SALMONN also said that at present, SALMONN is capable of English speech recognition, English-to-Chinese speech translation, emotion recognition, audio subtitle generation, music description and other important voice and audio tasks. At the same time, a variety of multilingual and cross-modal capabilities have emerged that have not been specially learned in model training. It covers tasks such as non-English speech recognition, speech translation from English to other languages (other than Chinese), summary and keyword extraction of speech content, audio-based story generation, audio Q & A, voice and audio joint reasoning, etc.

At present, the model has been released on GitHub, and the official Demo link to the project has been released at the same time, which can be learned 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.