Search
StepFun Launches StepAudio 2.5 ASR, Introduces MTP Technology to Reshape Speech Recognition Efficiency
18 hour ago /
Read about 0 minute
Author：小编
StepFun has unveiled its new-generation automatic speech recognition model, StepAudio 2.5 ASR, which boosts inference speed by 400%, reduces latency by 60%, cuts costs by 80%, and supports complete transcription of 30-minute audio files.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
