How to use deepspeech - 10 common examples

let parser = new argparse.ArgumentParser({addHelp: true, description: 'Running DeepSpeech inference.'});
parser.addArgument(['--model'], {required: true, help: 'Path to the model (protocol buffer binary file)'});
parser.addArgument(['--lm'], {help: 'Path to the language model binary file', nargs: '?'});
parser.addArgument(['--trie'], {help: 'Path to the language model trie file created with native_client/generate_trie', nargs: '?'});
parser.addArgument(['--audio'], {required: true, help: 'Path to the audio source to run (ffmpeg supported formats)'});
parser.addArgument(['--version'], {action: VersionAction, help: 'Print version and exits'});
let args = parser.parseArgs();

function totalTime(hrtimeValue) {
	return (hrtimeValue[0] + hrtimeValue[1] / 1000000000).toPrecision(4);
}

console.error('Loading model from file %s', args['model']);
const model_load_start = process.hrtime();
let model = new Ds.Model(args['model'], BEAM_WIDTH);
const model_load_end = process.hrtime(model_load_start);
console.error('Loaded model in %ds.', totalTime(model_load_end));

if (args['lm'] && args['trie']) {
	console.error('Loading language model from files %s %s', args['lm'], args['trie']);
	const lm_load_start = process.hrtime();
	model.enableDecoderWithLM(args['lm'], args['trie'], LM_ALPHA, LM_BETA);
	const lm_load_end = process.hrtime(lm_load_start);
	console.error('Loaded language model in %ds.', totalTime(lm_load_end));
}

// Default is 16kHz
const AUDIO_SAMPLE_RATE = 16000;

// Defines different thresholds for voice detection
// NORMAL: Suitable for high bitrate, low-noise data. May classify noise as voice, too.

};

let parser = new argparse.ArgumentParser({addHelp: true, description: 'Running DeepSpeech inference.'});
parser.addArgument(['--model'], {required: true, help: 'Path to the model (protocol buffer binary file)'});
parser.addArgument(['--scorer'], {help: 'Path to the scorer file', nargs: '?'});
parser.addArgument(['--audio'], {required: true, help: 'Path to the audio source to run (ffmpeg supported formats)'});
parser.addArgument(['--version'], {action: VersionAction, help: 'Print version and exits'});
let args = parser.parseArgs();

function totalTime(hrtimeValue) {
	return (hrtimeValue[0] + hrtimeValue[1] / 1000000000).toPrecision(4);
}

console.error('Loading model from file %s', args['model']);
const model_load_start = process.hrtime();
let model = new Ds.Model(args['model']);
const model_load_end = process.hrtime(model_load_start);
console.error('Loaded model in %ds.', totalTime(model_load_end));

if (args['scorer']) {
	console.error('Loading scorer from file %s', args['scorer']);
	const scorer_load_start = process.hrtime();
	model.enableExternalScorer(args['scorer']);
	const scorer_load_end = process.hrtime(scorer_load_start);
	console.error('Loaded scorer in %ds.', totalTime(scorer_load_end));
}

// Defines different thresholds for voice detection
// NORMAL: Suitable for high bitrate, low-noise data. May classify noise as voice, too.
// LOW_BITRATE: Detection mode optimised for low-bitrate audio.
// AGGRESSIVE: Detection mode best suited for somewhat noisy, lower quality audio.
// VERY_AGGRESSIVE: Detection mode with lowest miss-rate. Works well for most inputs.

const DeepSpeech = require('deepspeech');
const Fs = require('fs');
const Sox = require('sox-stream');
const MemoryStream = require('memory-stream');
const Duplex = require('stream').Duplex;
const Wav = require('node-wav');

let modelPath = './models/deepspeech-0.7.0-models.pbmm';

let model = new DeepSpeech.Model(modelPath);

let desiredSampleRate = model.sampleRate();

let scorerPath = './models/deepspeech-0.7.0-models.scorer';

model.enableExternalScorer(scorerPath);

let audioFile = process.argv[2] || './audio/2830-3980-0043.wav';

if (!Fs.existsSync(audioFile)) {
	console.log('file missing:', audioFile);
	process.exit();
}

const buffer = Fs.readFileSync(audioFile);
const result = Wav.decode(buffer);

getAsrModel() {
		const BEAM_WIDTH = config.services.HermodDeepSpeechAsrService.BEAM_WIDTH;
		const LM_ALPHA = config.services.HermodDeepSpeechAsrService.LM_ALPHA;
		const LM_BETA = config.services.HermodDeepSpeechAsrService.LM_BETA;
		const N_FEATURES = config.services.HermodDeepSpeechAsrService.N_FEATURES;
		const N_CONTEXT = config.services.HermodDeepSpeechAsrService.N_CONTEXT;
		var args = config.services.HermodDeepSpeechAsrService.files;
		
		console.error('Loading model from file %s', args['model']);
		const model_load_start = process.hrtime();
		let model = new Ds.Model(args['model'], N_FEATURES, N_CONTEXT, args['alphabet'], BEAM_WIDTH);
		const model_load_end = process.hrtime(model_load_start);
		console.error('Loaded model in %ds.', this.totalTime(model_load_end));

		if (args['lm'] && args['trie']) {
			console.error('Loading language model from files %s %s', args['lm'], args['trie']);
			const lm_load_start = process.hrtime();
			model.enableDecoderWithLM(args['alphabet'], args['lm'], args['trie'],
				LM_ALPHA, LM_BETA);
			const lm_load_end = process.hrtime(lm_load_start);
			console.error('Loaded language model in %ds.', this.totalTime(lm_load_end));
		}
		
		return model;
	}

VersionAction.prototype.call = function(parser) {
	Ds.printVersions();
	process.exit(0);
};

VersionAction.prototype.call = function(parser) {
	Ds.printVersions();
	process.exit(0);
};

function createModel(modelDir) {
	let modelPath = modelDir + '.pbmm';
	let scorerPath = modelDir + '.scorer';
	let model = new DeepSpeech.Model(modelPath);
	model.enableExternalScorer(scorerPath);
	return model;
}

function createModel(modelDir) {
	let modelPath = modelDir + '.pbmm';
	let scorerPath = modelDir + '.scorer';
	let model = new DeepSpeech.Model(modelPath);
	model.enableExternalScorer(scorerPath);
	return model;
}

function createModel(modelDir, options) {
	let modelPath = modelDir + '/output_graph.pbmm';
	let lmPath = modelDir + '/lm.binary';
	let triePath = modelDir + '/trie';
	let model = new DeepSpeech.Model(modelPath, options.BEAM_WIDTH);
	model.enableDecoderWithLM(lmPath, triePath, options.LM_ALPHA, options.LM_BETA);
	return model;
}