56 lines
1.7 KiB
JavaScript
56 lines
1.7 KiB
JavaScript
const WebSocket = require('ws');
|
|
const wss = new WebSocket.Server({ port: 8081 });
|
|
console.log('WebSocket server started on port 8081');
|
|
|
|
//we use https://hub.docker.com/r/onerahmet/openai-whisper-asr-webservice to transcribe the audio
|
|
//docker run -p 9009:9009 -d onerahmet/openai-whisper-asr-webservice
|
|
|
|
wss.on('connection', (ws) => {
|
|
console.log('Client ' + ws._socket.remoteAddress + ' connected');
|
|
ws.on('message', (data) => {
|
|
console.log('Received data from client: ' + data.length + ' bytes');
|
|
var request = require('request');
|
|
var formData = {
|
|
task: 'transcribe',
|
|
language: 'en-US',
|
|
output: 'json',
|
|
audio_file: {
|
|
value: data,
|
|
options: {
|
|
filename: 'audio.ogg',
|
|
contentType: 'audio/ogg'
|
|
}
|
|
}
|
|
};
|
|
request.post({url:'http://192.168.0.10:9009/asr', formData: formData}, function optionalCallback(err, httpResponse, body) {
|
|
if (err) {
|
|
return console.error('upload failed:', err);
|
|
}
|
|
console.log('Upload successful! Server responded with:', body);
|
|
ws.send(">>: " + body);
|
|
});
|
|
|
|
ws.send("Processing audio...");
|
|
});
|
|
});
|
|
|
|
function transcribeAudio(audioData) {
|
|
// Use a speech-to-text library to transcribe the audio data
|
|
//return transcription;
|
|
return "TEST";
|
|
}
|
|
|
|
|
|
// --- web server that servers client.html
|
|
const express = require('express');
|
|
const app = express();
|
|
const path = require('path');
|
|
|
|
app.get('/', (req, res) => {
|
|
res.sendFile(path.join(__dirname, 'client.html'));
|
|
});
|
|
|
|
app.listen(8080, () => {
|
|
console.log('Server listening on port 8080');
|
|
});
|