Back    Zoom +    Zoom -
Alibaba Tongyi Lab Launches Speech Recognition Large Model, Fun-ASR1.5, Covering 30 Languages
Recommend
21
Positive
30
Negative
11
Alibaba Tongyi Lab officially launched its speech recognition large model, Fun-ASR1.5.

Based on an unified large model architecture, this single model can cover 30 languages, seven major Chinese dialect groups and more than 20 regional accents. It can also accurately transcribe classical Chinese poetry recitations.

Related News Citi: Mainland Crackdown on "Ghost Takeaways" Helps Eliminate and Ease Regulatory Uncertainty
Fun-ASR1.5 has been officially launched on the Alibaba Cloud's Bailian platform, providing API services to clients across various industries including education, media, finance, technology and culture.

Auto-translated by AI

AASTOCKS Financial News