OpenAI Releases 1.6 Billion Parameter Multilingual Speech Recognition AI Whisper

OpenAI recently released Whisper, a 1.6 billion parameter AI model that can transcribe and translate speech audio from 97 different languages. Whisper was trained on 680,000 hours of audio data collected from the web and shows robust zero-shot performance on a wide range of automated speech recognition (ASR) tasks.

ai deep learning ml & data engineering neural networks news openai releases speech speech recognition whisper