Speech-to-Text

import { transformers } from '@localmode/transformers';
import { transcribe } from '@localmode/core';

const model = transformers.speechToText('onnx-community/moonshine-tiny-ONNX');

// Record audio from microphone
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
const recorder = new MediaRecorder(stream, { mimeType: 'audio/webm' });
const chunks: Blob[] = [];

recorder.ondataavailable = (e) => chunks.push(e.data);
recorder.start();

// Stop recording after some time...
recorder.stop();

recorder.onstop = async () => {
  const audioBlob = new Blob(chunks, { type: 'audio/webm' });

  const { text } = await transcribe({
    model,
    audio: audioBlob,
    abortSignal: controller.signal,
  });

  console.log('Transcription:', text);
};

const { text, segments } = await transcribe({
  model,
  audio: audioBlob,
  returnTimestamps: true,
});

segments?.forEach((s) => {
  console.log(`[${s.start.toFixed(1)}s - ${s.end.toFixed(1)}s] ${s.text}`);
});