According to Alibaba Cloud official WeChat news, on December 22, Alibaba DAMO Academy released a new generation of speech recognition model Paraformer.

This is the industry’s first non-autoregressive end-to-end speech recognition model. At present, the model is open sourced to the whole society in the Mota community, and is applicable to many scenarios such as voice input method, intelligent customer service, car navigation, meeting minutes, etc.