Speech recognition macromodel

August 23 news, nail, Tongyi Labs voice team announced yesterday, joined forces to launch a new generation of speech recognition big model Fun-ASR, can understand home improvement, animal husbandry and other ten industry black words, and support enterprise exclusive model custom training. At present, Fun-ASR has been integrated into a number of functional modules of Nail, including meeting subtitles and simultaneous transmission, intelligent minutes, voice assistant and so on. 1AI learned that Fun-ASR has been integrated into several functional modules of Nail, including meeting subtitle and simultaneous transmission, intelligent minutes, voice assistant, etc., aiming to build a set of stable, efficient and easy to expand voice...

November 3, 2011 - China Telecom's Institute of Artificial Intelligence (TeleAI) released the industry's first multi-dialect speech recognition model in May this year, which supports the free mixing of 30 dialects. Less than half a year later, TeleAI's Star Speech Recognition Model has upgraded its multi-dialect capability again, conquering dialects such as Zhanjiang, Yibin, Luoyang and Yantai, raising the number of dialects from 30 to 40, and introducing the recognition of English. Compared with traditional labeled training methods, TeleAI pre-trains speech recognition models...