f

main.py

@@ -1,16 +1,14 @@
 from fastapi import FastAPI, WebSocket, WebSocketDisconnect, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse, HTMLResponse
-import sounddevice as sd
 import numpy as np
 import librosa
+import soundfile as sf
 import joblib
 import uvicorn
-import threading
-import asyncio
 import logging
 import io
-import soundfile as sf
+from pydub import AudioSegment
 from typing import List
 
 logging.basicConfig(level=logging.INFO)
@@ -79,10 +77,13 @@ def extract_features(audio):
 
 async def process_audio_data(audio_data):
     try:
-        with io.BytesIO(audio_data) as audio_io:
-            audio_io.seek(0)
-            audio, sr = sf.read(audio_io, dtype='float32')
-    except RuntimeError as e:
+        # Convert audio data from webm/ogg to wav format using pydub
+        audio_segment = AudioSegment.from_file(io.BytesIO(audio_data), format="webm")
+        wav_io = io.BytesIO()
+        audio_segment.export(wav_io, format="wav")
+        wav_io.seek(0)
+        audio, sr = sf.read(wav_io, dtype='float32')
+    except Exception as e:
         logger.error(f"Failed to read audio data: {e}")
         return
 
@@ -98,7 +99,6 @@ async def process_audio_data(audio_data):
     
     await manager.send_message(result)
 
-
 @app.post("/start_detection")
 async def start_detection():
     global is_detecting

templates/index.html

@@ -63,7 +63,7 @@
                 const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
                 logMessage('Microphone access granted', 'info');
 
-                mediaRecorder = new MediaRecorder(stream, { mimeType: 'audio/wav' });
+                mediaRecorder = new MediaRecorder(stream, { mimeType: 'audio/webm' });
                 mediaRecorder.ondataavailable = function(event) {
                     if (websocket && websocket.readyState === WebSocket.OPEN) {
                         websocket.send(event.data);
@@ -81,7 +81,7 @@
                 const result = await response.json();
                 logMessage(`Detection started: ${result.status}`, 'info');
 
-                websocket = new WebSocket(`ws://${window.location.host}/ws`);
+                websocket = new WebSocket(`wss://${window.location.host}/ws`);
                 websocket.onmessage = function(event) {
                     const data = event.data;
                     logMessage(`Detected ${data} audio`, data);
@@ -97,6 +97,7 @@
         }
 
 
+
         async function stopDetection() {
             if (!isDetecting) {
                 logMessage('Detection is not running...', 'info');