113 lines
2.7 KiB
JavaScript
113 lines
2.7 KiB
JavaScript
const fs = require('fs');
|
|
// const portAudio = require('naudiodon');
|
|
// Imports the Google Cloud client library
|
|
const speech = require('@google-cloud/speech');
|
|
const portAudio = require('naudiodon');
|
|
|
|
// Create a stream to pipe into the AudioOutput
|
|
// Note that this does not strip the WAV header so a click will be heard at the beginning
|
|
const rs = fs.createReadStream('rawAudio.wav');
|
|
const WebSocket = require("ws")
|
|
// Start piping data and start streaming
|
|
const {Writable} = require('stream');
|
|
const ws = new WebSocket("ws://localhost:8080");
|
|
//const duplex = WebSocket.createWebSocketStream(ws, { encoding: 'binary' });
|
|
|
|
let audioChunks = [];
|
|
const audioInputStreamTransform = new Writable({
|
|
write(chunk, encoding, next) {
|
|
// console.log(chunk)
|
|
// ws send chunk
|
|
audioChunks.push(chunk);
|
|
next();
|
|
},
|
|
|
|
final() {
|
|
console.log(audioChunks)
|
|
ws.send(audioChunks)
|
|
// stop ws transer
|
|
},
|
|
});
|
|
|
|
|
|
// Creates a client
|
|
const client = new speech.SpeechClient();
|
|
|
|
/**
|
|
* TODO(developer): Uncomment the following lines before running the sample.
|
|
*/
|
|
const filename = './rawAudio.wav';
|
|
const encoding = 'LINEAR16';
|
|
const sampleRateHertz = 16000;
|
|
const languageCode = 'en-US';
|
|
|
|
const config = {
|
|
encoding: encoding,
|
|
sampleRateHertz: sampleRateHertz,
|
|
languageCode: languageCode,
|
|
};
|
|
const audio = {
|
|
content: fs.readFileSync(filename).toString('base64'),
|
|
};
|
|
|
|
// const request = {
|
|
// config: config,
|
|
// audio: audio,
|
|
// };
|
|
|
|
// Detects speech in the audio file
|
|
async function test() {
|
|
const [response] = await client.recognize(request);
|
|
const transcription = response.results
|
|
.map(result => result.alternatives[0].transcript)
|
|
.join('\n');
|
|
console.log('Transcription: ', transcription);
|
|
}
|
|
|
|
// test();
|
|
|
|
const request = {
|
|
config,
|
|
interimResults: true,
|
|
};
|
|
|
|
const speechCallback = (data) => {
|
|
console.log(
|
|
`Transcription: ${data.results[0].alternatives[0].transcript}`
|
|
)
|
|
}
|
|
|
|
const recognizeStream = client
|
|
.streamingRecognize(request)
|
|
.on('error', err => {
|
|
if (err.code === 11) {
|
|
// restartStream();
|
|
} else {
|
|
console.error('API request error ' + err);
|
|
}
|
|
})
|
|
.on('data', speechCallback);
|
|
|
|
// Create an instance of AudioIO with inOptions (defaults are as below), which will return a ReadableStream
|
|
const audioOptions = {
|
|
channelCount: 2,
|
|
sampleFormat: portAudio.sampleFormat16Bit,
|
|
sampleRate: 16000,
|
|
deviceId: -1, // Use -1 or omit the deviceId to select the default device
|
|
closeOnError: false // Close the stream if an audio error is detected, if set false then just log the error
|
|
}
|
|
|
|
let audioData = [];
|
|
const ai = new portAudio.AudioIO({
|
|
inOptions: audioOptions
|
|
});
|
|
// ai.on('data', (d) => {
|
|
// audioData.push(d.toString('binary'))
|
|
// })
|
|
ai.pipe(audioInputStreamTransform)
|
|
ai.start();
|
|
setTimeout(() => {
|
|
ai.quit();
|
|
}, 2000)
|
|
|
|
|