Artificial intelligence · 2022
Whisper
An open speech recogniser trained on 680,000 hours of multilingual audio.
OpenAI released Whisper's weights in September 2022. Its robustness to accents and noise approached human transcription, and as open source it became the default speech-to-text engine for apps and hobbyists.
What it built on 2
What it led to 3
Related measurements
The dashed line marks when it first worked.
Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)
ML hardware FLOP/s per dollar Source: Epoch AI, ML hardware (CC BY 4.0)