Alibaba Tongyi Laboratory Launches Speech Recognition Large Model Fun-ASR1.5

April 20th, Alibaba Tongyi Laboratory officially launched the speech recognition large model Fun-ASR1.5. According to the introduction, it is based on a unified large model architecture, capable of covering 30 languages, seven major Chinese dialect systems, and over 20 regional accents with a single model. It can also accurately transcribe classical poetry recitations. Currently, Fun-ASR1.5 is officially available on Alibaba Cloud’s Bailing platform, providing API services to clients across industries such as education, media, finance, technology, and culture. (Jiemian News)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin