aqasemi / whisper-jax

Faster and cheaper Whisper-AI Large-v2 responses. JAX implementation of OpenAI's Whisper model for up to 15x speed-up (doesn't support TPU).

  • Public
  • 110.8K runs
  • T4

Input

Video Player is loading.
Current Time 00:00:000
Duration 00:00:000
Loaded: 0%
Stream Type LIVE
Remaining Time 00:00:000
 
1x
*file

Audio file

Output

transcription

My name is King Canute and I have come to kill you for the crimes your father committed against my people. Well I hate to disappoint you.

detected_language

Detected language 'en' with probability 0.979980
Generated in

Run time and cost

This model costs approximately $0.036 to run on Replicate, or 27 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 T4 GPU hardware. Predictions typically complete within 3 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.