Loading...
Loading...
Browse all stories on DeepNewz
VisitaiOla Unveils Open-Source Whisper-Medusa, 50% Faster than OpenAI's Whisper
Aug 2, 2024, 02:14 AM
Israeli company aiOla has introduced an ultra-fast, open-source speech recognition model called Whisper-Medusa, which significantly outperforms OpenAI's Whisper. The Whisper-Medusa model incorporates a multi-head attention mechanism, enabling it to adapt instantly to new jargon without requiring retraining. aiOla's model is reported to be 50% faster than OpenAI's Whisper, marking a notable advancement in the field of automatic speech recognition.
View original story
Apple • 25%
Google • 25%
Microsoft • 25%
Other • 25%
Google • 25%
Microsoft • 25%
Amazon • 25%
Other • 25%
Amazon • 25%
Google • 25%
Microsoft • 25%
Other • 25%
Google Cloud • 25%
Microsoft Azure • 25%
Amazon Web Services • 25%
Other • 25%
Google • 25%
Microsoft • 25%
Amazon • 25%
IBM • 25%
Meta • 25%
Google • 25%
IBM • 25%
Other • 25%
Google • 25%
IBM • 25%
Microsoft • 25%
Amazon • 25%
Google • 25%
Microsoft • 25%
Amazon • 25%
Other • 25%
Google • 25%
Microsoft • 25%
Amazon • 25%
Other • 25%
Google • 25%
Microsoft • 25%
Amazon • 25%
Other • 25%
Electronic Arts • 25%
Ubisoft • 25%
Activision Blizzard • 25%
Other • 25%
Other • 25%
aiOla's Whisper-Medusa • 25%
OpenAI's Whisper • 25%
Google's Speech-to-Text • 25%