openai/
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
Please upload an audio file
You need to login to use this model
LoginSettings
task to perform 2
optional text to provide as a prompt for the first window.. (Default: empty)
temperature to use for sampling (Default: 0)
language that the audio is in; uses detected language if None; use two letter language code (ISO 639-1) (e.g. en, de, ja) 101
chunk level, either 'segment' or 'word' 2
Chunk Length S
chunk length in seconds to split audio (Default: 30, 1 ≤ chunk_length_s ≤ 30)
Run models at scale with our fully managed GPU infrastructure, delivering enterprise-grade uptime at the industry's best rates.