Search
Kimi Unveils Universal Audio Foundation Model: Kimi-Audio
2025-04-27 /
Read about 0 minute
Author：小编
Kimi has introduced a groundbreaking open-source project, Kimi-Audio, designed as a versatile audio foundation model. This model excels in a wide array of tasks, including speech recognition, audio understanding, audio-to-text conversion, and speech dialogues. It has surpassed its peers, achieving state-of-the-art (SOTA) performance in over a dozen audio benchmark tests, securing the top spot overall. The model's code, checkpoints, and evaluation toolkit are now freely available on Github.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
