Automatic Speech Recognition

Basic usage

Send an audio file to an ASR model to generate text.

import Bytez from 'bytez.js'

const sdk = new Bytez("BYTEZ_KEY");
const model = sdk.model("facebook/data2vec-audio-base-960h");

await model.create()

const audio = "https://huggingface.co/datasets/huggingfacejs/tasks/resolve/main/automatic-speech-recognition/input.flac"
const { error, output } = await model.run({ url: audio });

console.log({ error, output })

You can send the via url or base64 data URL.

We recommend url for better performance, as base64 increases payload size.

Audio Classification Chat

Model API