By open-sourcing Whisper, OpenAI hopes to introduce a new foundation model that others can build on in the future to improve speech processing and accessibility tools. OpenAI has a significant ...

In the past month, Whisper was downloaded over 4.2 million times from the open-source AI platform HuggingFace, with the tool being the most popular speech recognition model on the website.

I'm working on a new project with @film_girl to create a free, secure, and easy-to-use transcription app for journalists, powered by @openai 's whisper ML model. If you're interested in ...

Hospitals routinely use a tool powered by OpenAI’s Whisper transcription model, which researchers find can hallucinate entire passages during periods of silence.

Whisper’s large-v2 model in the API provides much faster and cost-effective results, OpenAI said. Whisper accepts files in multiple formats including M4A, MP3, MP4, MPEG, MPGA, WAV and WEBM.

OpenAI has released an open-source transcription program called Whisper. While it’s mainly aimed at researchers and developers, it turns out to be really useful for journalists, too.