Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
Audio file
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run aqasemi/whisper-jax using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "aqasemi/whisper-jax:fb09fe931a654f989fffaabdf46b7b5c69f8ace6b89555d84eae6173d49724f1", { input: { audio: "https://replicate.delivery/pbxt/JFp9IPOzTHfQ0JmA5NgaOHQWM5T0CAhTsrLnFOXDdFljSjbe/canute.mp3" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
import replicate
output = replicate.run( "aqasemi/whisper-jax:fb09fe931a654f989fffaabdf46b7b5c69f8ace6b89555d84eae6173d49724f1", input={ "audio": "https://replicate.delivery/pbxt/JFp9IPOzTHfQ0JmA5NgaOHQWM5T0CAhTsrLnFOXDdFljSjbe/canute.mp3" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "aqasemi/whisper-jax:fb09fe931a654f989fffaabdf46b7b5c69f8ace6b89555d84eae6173d49724f1", "input": { "audio": "https://replicate.delivery/pbxt/JFp9IPOzTHfQ0JmA5NgaOHQWM5T0CAhTsrLnFOXDdFljSjbe/canute.mp3" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
transcription
detected_language
{ "completed_at": "2023-07-29T00:07:00.002195Z", "created_at": "2023-07-29T00:06:58.908609Z", "data_removed": false, "error": null, "id": "uv3j2njb3ppg4i2kqnfzorpzmi", "input": { "audio": "https://replicate.delivery/pbxt/JFp9IPOzTHfQ0JmA5NgaOHQWM5T0CAhTsrLnFOXDdFljSjbe/canute.mp3" }, "logs": "Transcribe with large-v2 model", "metrics": { "predict_time": 1.115406, "total_time": 1.093586 }, "output": { "transcription": " You must be the boy King Edmund", "detected_language": "Detected language 'en' with probability 0.976562" }, "started_at": "2023-07-29T00:06:58.886789Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/uv3j2njb3ppg4i2kqnfzorpzmi", "cancel": "https://api.replicate.com/v1/predictions/uv3j2njb3ppg4i2kqnfzorpzmi/cancel" }, "version": "fb09fe931a654f989fffaabdf46b7b5c69f8ace6b89555d84eae6173d49724f1" }
Transcribe with large-v2 model
Choose a file from your machine
Hint: you can also drag files onto the input