Alibaba releases the large-scale speech recognition model Fun-ASR1.5

Mars Finance reports that on April 20th, Alibaba released the end-to-end speech recognition large model Fun-ASR1.5, which does not require preset language tags and can accurately recognize 30 languages with a single model. Previously, Fun-ASR1.0 had been used in DingTalk AI transcription, DingTalk A1 recorder, and other smart hardware. The newly upgraded version 1.5 covers the seven major Chinese dialect systems and more than twenty regional accents, and enhances specialized recognition for classical poetry recitation, expanding application scenarios to multinational companies, international conferences, multilingual live streaming, county-level government services, and classical poetry education.

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