iFlytek releases speech foundation large model Spark-Audio-1.0-Preview trained on fully domestic computing power
iFlytek launched Spark-Audio-1.0-Preview today, a speech foundation large model trained on fully domestic computing power, which can directly understand speech, supports recognition of 99 languages and 202 dialects, and leads in complex environments and multiple evaluations.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome