c1
parent
b3ac3498fe
commit
878411e55b
111
server.js
111
server.js
|
|
@ -10,7 +10,7 @@ app.use(express.static('public'));
|
|||
|
||||
const server = app.listen(PORT, () => {
|
||||
console.log(`Server running on http://localhost:${PORT}`);
|
||||
console.log('Using Python SpeechRecognition with PocketSphinx for local STT');
|
||||
console.log('Using Vosk for local STT processing');
|
||||
});
|
||||
|
||||
const wss = new WebSocket.Server({ server });
|
||||
|
|
@ -18,6 +18,8 @@ const wss = new WebSocket.Server({ server });
|
|||
class SpeechProcessor {
|
||||
constructor() {
|
||||
this.pythonProcess = null;
|
||||
this.activeRequests = new Map();
|
||||
this.requestCounter = 0;
|
||||
this.initializePythonProcess();
|
||||
}
|
||||
|
||||
|
|
@ -33,16 +35,60 @@ class SpeechProcessor {
|
|||
|
||||
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) {
|
||||
|
|
@ -50,47 +96,28 @@ class SpeechProcessor {
|
|||
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);
|
||||
|
||||
// Read response
|
||||
let responseLength = null;
|
||||
let responseData = Buffer.alloc(0);
|
||||
let expecting = 'length';
|
||||
|
||||
const onData = (data) => {
|
||||
responseData = Buffer.concat([responseData, data]);
|
||||
|
||||
if (expecting === 'length' && responseData.length >= 4) {
|
||||
responseLength = responseData.readUInt32BE(0);
|
||||
responseData = responseData.slice(4);
|
||||
expecting = 'data';
|
||||
}
|
||||
|
||||
if (expecting === 'data' && responseData.length >= responseLength) {
|
||||
const jsonData = responseData.slice(0, responseLength);
|
||||
this.pythonProcess.stdout.removeListener('data', onData);
|
||||
|
||||
try {
|
||||
const result = JSON.parse(jsonData.toString());
|
||||
resolve(result);
|
||||
} catch (error) {
|
||||
reject(error);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
this.pythonProcess.stdout.on('data', onData);
|
||||
|
||||
// Timeout after 10 seconds
|
||||
setTimeout(() => {
|
||||
this.pythonProcess.stdout.removeListener('data', onData);
|
||||
if (this.activeRequests.has(requestId)) {
|
||||
this.activeRequests.delete(requestId);
|
||||
reject(new Error('Speech processing timeout'));
|
||||
}
|
||||
}, 10000);
|
||||
});
|
||||
}
|
||||
|
|
@ -101,18 +128,32 @@ 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 && result.text) {
|
||||
if (result.success) {
|
||||
if (result.is_final && result.text && result.text !== lastFinalText) {
|
||||
lastFinalText = result.text;
|
||||
ws.send(JSON.stringify({
|
||||
type: 'transcription',
|
||||
text: result.text
|
||||
text: result.text,
|
||||
is_final: true
|
||||
}));
|
||||
console.log('Transcription:', result.text);
|
||||
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({
|
||||
|
|
@ -136,6 +177,8 @@ wss.on('connection', (ws) => {
|
|||
|
||||
ws.on('close', () => {
|
||||
console.log('Client disconnected');
|
||||
lastFinalText = '';
|
||||
lastPartialText = '';
|
||||
});
|
||||
|
||||
ws.on('error', (error) => {
|
||||
|
|
|
|||
Loading…
Reference in New Issue