This is code to add to Watson's Speech to Text service to improve its accuracy. Blogpost explaining this is at https://watson-tricks.blogspot.ie

createModel.js

var SpeechToTextV1 = require('watson-developer-cloud/speech-to-text/v1');
var speech_to_text = new SpeechToTextV1 ({
  username: 'username',
  password: 'password'
});

var params = {
  name: 'DC Example model',
  'base_model_name': 'en-US_BroadbandModel',
  description: 'Example custom language model'
};

speech_to_text.createCustomization(params, function(error, customization) {
  if (error)
    console.log('Error:', error);
  else
    console.log(JSON.stringify(customization, null, 2));
});

transcribe.js

'use strict';
const util = require('util');
const SpeechToTextV1 = require('watson-developer-cloud/speech-to-text/v1');

const fs = require('fs');

const speech_to_text = new SpeechToTextV1({
    username: 'username',
  password: 'password'
});





speech_to_text.createSession({}, function(error, session) {
  if (error)
    console.log('Error:', error);
  else
    console.log(JSON.stringify(session, null, 2));
});

//include customisation id to tell it which model to use
const params = {
    //you can put in audio here as well
    //	audio: fs.createReadStream(__dirname + '/DavidCarDemo.wav'),
  content_type: 'audio/wav',
  customization_id: '06da5480-915c-11e7-bed0-ef2634fd8461'
};



speech_to_text.recognize(params, function(error, transcript) {
  if (error)
    console.log('Error:', error);
  else
    console.log(JSON.stringify(transcript, null, 2));
});

// create the stream
const recognizeStream = speech_to_text.createRecognizeStream(params);

// pipe in some audio. This is my file you can use your own
fs.createReadStream(__dirname + '/DavidCarDemo.wav').pipe(recognizeStream);

// and pipe out the transcription
recognizeStream.pipe(fs.createWriteStream('transcription.txt'));

// listen for 'data' events for just the final text
// listen for 'results' events to get the raw JSON with interim results, timings, etc.

recognizeStream.setEncoding('utf8'); // to get strings instead of Buffers from `data` events

//['data', 'results', 'speaker_labels', 'error', 'close'].forEach(function(eventName) {
['data', 'speaker_labels', 'error', 'close'].forEach(function(eventName) {
  recognizeStream.on(eventName, console.log.bind(console, eventName + ' event: '));
});