Whisper is a general-purpose speech recognition model.
This model costs approximately $0.047 to run on Replicate, or 21 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 65 seconds. The predict time for this model varies significantly based on the inputs.
Whisper is a Transformer based encoder-decoder model, also referred to as a sequence-to-sequence model.
It was trained on 1 million hours of weakly labeled audio and 4 million hours of pseudolabeled audio collected using Whisper large-v2.
See the full model card here