187 lines
6.4 KiB
JavaScript
187 lines
6.4 KiB
JavaScript
const express = require('express');
|
|
const WebSocket = require('ws');
|
|
const { spawn } = require('child_process');
|
|
const fs = require('fs');
|
|
|
|
const app = express();
|
|
const PORT = 5080;
|
|
|
|
app.use(express.static('public'));
|
|
|
|
const server = app.listen(PORT, () => {
|
|
console.log(`Server running on http://localhost:${PORT}`);
|
|
console.log('Using Vosk for local STT processing');
|
|
});
|
|
|
|
const wss = new WebSocket.Server({ server });
|
|
|
|
class SpeechProcessor {
|
|
constructor() {
|
|
this.pythonProcess = null;
|
|
this.activeRequests = new Map();
|
|
this.requestCounter = 0;
|
|
this.initializePythonProcess();
|
|
}
|
|
|
|
initializePythonProcess() {
|
|
try {
|
|
this.pythonProcess = spawn('python3', ['speech_processor.py'], {
|
|
stdio: ['pipe', 'pipe', 'pipe']
|
|
});
|
|
|
|
this.pythonProcess.stderr.on('data', (data) => {
|
|
console.error('Python process error:', data.toString());
|
|
});
|
|
|
|
this.pythonProcess.on('close', (code) => {
|
|
console.log(`Python process closed with code ${code}`);
|
|
// Clear active requests
|
|
this.activeRequests.clear();
|
|
// Restart process if it dies
|
|
setTimeout(() => this.initializePythonProcess(), 1000);
|
|
});
|
|
|
|
// Setup stdout data handler
|
|
this.pythonProcess.stdout.on('data', (data) => {
|
|
this.handlePythonOutput(data);
|
|
});
|
|
|
|
console.log('Python speech processor initialized');
|
|
} catch (error) {
|
|
console.error('Failed to initialize Python process:', error);
|
|
}
|
|
}
|
|
|
|
handlePythonOutput(data) {
|
|
let buffer = data;
|
|
|
|
while (buffer.length > 0) {
|
|
// If we're expecting a length prefix
|
|
if (buffer.length >= 4) {
|
|
const length = buffer.readUInt32BE(0);
|
|
buffer = buffer.slice(4);
|
|
|
|
// If we have enough data for the complete message
|
|
if (buffer.length >= length) {
|
|
const messageData = buffer.slice(0, length);
|
|
buffer = buffer.slice(length);
|
|
|
|
try {
|
|
const result = JSON.parse(messageData.toString());
|
|
const { requestId } = result;
|
|
|
|
if (requestId && this.activeRequests.has(requestId)) {
|
|
const { resolve } = this.activeRequests.get(requestId);
|
|
this.activeRequests.delete(requestId);
|
|
resolve(result);
|
|
}
|
|
} catch (error) {
|
|
console.error('Error parsing Python output:', error);
|
|
}
|
|
} else {
|
|
// Not enough data yet, wait for more
|
|
break;
|
|
}
|
|
} else {
|
|
// Not enough data for length prefix yet
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
async processAudio(audioBuffer) {
|
|
return new Promise((resolve, reject) => {
|
|
if (!this.pythonProcess) {
|
|
reject(new Error('Python process not available'));
|
|
return;
|
|
}
|
|
|
|
const requestId = this.requestCounter++;
|
|
this.activeRequests.set(requestId, { resolve, reject });
|
|
|
|
// Send audio data length first
|
|
const lengthBuffer = Buffer.allocUnsafe(4);
|
|
lengthBuffer.writeUInt32BE(audioBuffer.length, 0);
|
|
this.pythonProcess.stdin.write(lengthBuffer);
|
|
|
|
// Send request ID
|
|
const idBuffer = Buffer.allocUnsafe(4);
|
|
idBuffer.writeUInt32BE(requestId, 0);
|
|
this.pythonProcess.stdin.write(idBuffer);
|
|
|
|
// Send audio data
|
|
this.pythonProcess.stdin.write(audioBuffer);
|
|
|
|
// Timeout after 10 seconds
|
|
setTimeout(() => {
|
|
if (this.activeRequests.has(requestId)) {
|
|
this.activeRequests.delete(requestId);
|
|
reject(new Error('Speech processing timeout'));
|
|
}
|
|
}, 10000);
|
|
});
|
|
}
|
|
}
|
|
|
|
const speechProcessor = new SpeechProcessor();
|
|
|
|
wss.on('connection', (ws) => {
|
|
console.log('Client connected');
|
|
|
|
let lastFinalText = '';
|
|
let lastPartialText = '';
|
|
|
|
ws.on('message', async (data) => {
|
|
try {
|
|
if (Buffer.isBuffer(data)) {
|
|
// Raw audio data received
|
|
const result = await speechProcessor.processAudio(data);
|
|
|
|
if (result.success) {
|
|
if (result.is_final && result.text && result.text !== lastFinalText) {
|
|
lastFinalText = result.text;
|
|
ws.send(JSON.stringify({
|
|
type: 'transcription',
|
|
text: result.text,
|
|
is_final: true
|
|
}));
|
|
console.log('Final Transcription:', result.text);
|
|
} else if (!result.is_final && result.text && result.text !== lastPartialText) {
|
|
lastPartialText = result.text;
|
|
ws.send(JSON.stringify({
|
|
type: 'partial_transcription',
|
|
text: result.text,
|
|
is_final: false
|
|
}));
|
|
}
|
|
} else if (!result.success) {
|
|
console.error('STT Error:', result.error);
|
|
ws.send(JSON.stringify({
|
|
type: 'error',
|
|
message: result.error
|
|
}));
|
|
}
|
|
} else {
|
|
// JSON message received
|
|
const message = JSON.parse(data);
|
|
console.log('Received message:', message);
|
|
}
|
|
} catch (error) {
|
|
console.error('Error processing message:', error);
|
|
ws.send(JSON.stringify({
|
|
type: 'error',
|
|
message: 'Error processing audio'
|
|
}));
|
|
}
|
|
});
|
|
|
|
ws.on('close', () => {
|
|
console.log('Client disconnected');
|
|
lastFinalText = '';
|
|
lastPartialText = '';
|
|
});
|
|
|
|
ws.on('error', (error) => {
|
|
console.error('WebSocket error:', error);
|
|
});
|
|
}); |