OpenAI
OpenAI develops Whisper and other open-source models alongside their proprietary GPT series, focusing on safe AGI development.
Founded
2015
Headquarters
San Francisco, California
Focus Areas
Speech RecognitionLanguage ModelsSafety
Philosophy
"Ensure AGI benefits all of humanity"
Models from OpenAI
Whisper Large V3
audioState-of-the-art speech recognition model supporting 99 languages with exceptional accuracy.
1.55BMIT
Whisper Medium
audioBalanced speech recognition model offering good accuracy with reasonable resource usage.
769MMIT
Whisper Small
audioCompact speech recognition for edge deployment and real-time applications.
244MMIT
Whisper Tiny
audioUltra-compact speech recognition for extreme edge deployment.
39MMIT
Whisper Base
audioBalanced speech recognition model for general use.
74MMIT