Upload 15 files

app.py

@@ -0,0 +1,99 @@
+import os
+import pickle
+import joblib
+import numpy as np
+from flask_cors import CORS
+from flask import Flask, request, render_template, jsonify
+from werkzeug.utils import secure_filename
+from extract import extract_features  # Import feature extractor
+
+# Initialize Flask app
+app = Flask(__name__)
+CORS(app)  # Allow all cross-origin requests
+
+# Set upload folder and allowed file types
+UPLOAD_FOLDER = "uploads"
+ALLOWED_EXTENSIONS = {"wav", "mp3", "ogg", "m4a"}
+app.config["UPLOAD_FOLDER"] = UPLOAD_FOLDER
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+
+# Load trained model, scaler, and feature list
+model_path = "models/gender_model_lr.pkl"
+scaler_path = "models/scaler_gender_model_lr.pkl"
+feature_list_path = "models/feature_list.pkl"
+
+model = joblib.load(model_path)
+scaler = joblib.load(scaler_path)
+with open(feature_list_path, "rb") as f:
+    feature_list = pickle.load(f)
+
+print("✅ Model, Scaler, and Feature List Loaded Successfully!")
+
+# Function to check valid file extensions
+def allowed_file(filename):
+    return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
+
+# Route to render the HTML interface
+@app.route("/")
+def index():
+    return render_template("index.html")
+
+# Route to handle file upload and prediction
+@app.route("/predict", methods=["POST"])
+def predict():
+    if "audio" not in request.files:
+        print("❌ No file uploaded")
+        return jsonify({"error": "No file uploaded"}), 400
+    
+    file = request.files["audio"]
+    print(f"📥 Received file: {file.filename}, Type: {file.content_type}")  # ✅ Debugging line
+
+    if file.filename == "":
+        return jsonify({"error": "No selected file"}), 400
+
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        filepath = os.path.join(app.config["UPLOAD_FOLDER"], filename)
+        file.save(filepath)
+
+        print(f"🟢 Processing file: {filename}")
+
+        try:
+            # Extract features
+            features = extract_features(filepath)
+            if features is None:
+                return jsonify({"error": "Feature extraction failed"}), 500
+            
+            print(f"🟢 Extracted {len(features)} features.")
+
+            # Scale features
+            features_scaled = scaler.transform([features])
+            print("🟢 Features scaled successfully.")
+
+            # Predict gender
+            prediction = model.predict(features_scaled)[0]
+            confidence = model.predict_proba(features_scaled)[0]
+            print("🟢 Prediction completed.")
+
+            # Format response
+            result = {
+                "gender": "Female" if prediction == 1 else "Male",
+                "confidence": float(max(confidence)),
+                "age_group": "Unknown"  # Temporary fix to avoid breaking frontend
+            }
+
+            print(f"✅ Result: {result}")
+
+            return jsonify(result)
+
+        except Exception as e:
+            print(f"❌ Error: {e}")
+            return jsonify({"error": str(e)}), 500
+        finally:
+            os.remove(filepath)  # Delete temp file
+
+    return jsonify({"error": "Invalid file format"}), 400
+
+# Run Flask app
+if __name__ == "__main__":
+    app.run(debug=True, use_reloader=False)  # Disable reloader

extract.py

@@ -0,0 +1,56 @@
+import librosa
+import numpy as np
+
+def extract_features(file_path):
+    try:
+        print(f"🟢 Processing file: {file_path}")
+        
+        # Load audio with fixed sample rate
+        y, sr = librosa.load(file_path, sr=16000)
+        
+        # Trim or pad audio to exactly 5 seconds
+        target_length = sr * 5
+        if len(y) > target_length:
+            start_sample = np.random.randint(0, len(y) - target_length)
+            y = y[start_sample:start_sample + target_length]
+        elif len(y) < target_length:
+            y = np.pad(y, (0, target_length - len(y)), mode='constant')
+        
+        print("✅ Audio loaded and standardized (5s, 16kHz)")
+        
+        # Extract features
+        mfcc = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
+        chroma = librosa.feature.chroma_stft(y=y, sr=sr)
+        spec_contrast = librosa.feature.spectral_contrast(y=y, sr=sr)
+        zcr = librosa.feature.zero_crossing_rate(y)
+        rms = librosa.feature.rms(y=y)
+        centroid = librosa.feature.spectral_centroid(y=y, sr=sr)
+        bandwidth = librosa.feature.spectral_bandwidth(y=y, sr=sr)
+        rolloff = librosa.feature.spectral_rolloff(y=y, sr=sr)
+        hnr = librosa.effects.harmonic(y)
+        pitches, _ = librosa.piptrack(y=y, sr=sr)
+        
+        # Aggregate features (mean + std for each feature)
+        features = {
+            "mfcc": np.concatenate([np.mean(mfcc, axis=1), np.std(mfcc, axis=1)]),
+            "chroma": np.concatenate([np.mean(chroma, axis=1), np.std(chroma, axis=1)]),
+            "spectral_contrast": np.concatenate([np.mean(spec_contrast, axis=1), np.std(spec_contrast, axis=1)]),
+            "zcr": [np.mean(zcr), np.std(zcr)],
+            "rms": [np.mean(rms), np.std(rms)],
+            "centroid": [np.mean(centroid), np.std(centroid)],
+            "bandwidth": [np.mean(bandwidth), np.std(bandwidth)],
+            "rolloff": [np.mean(rolloff), np.std(rolloff)],
+            "hnr": [np.mean(hnr), np.std(hnr)],
+            "pitch": [np.mean(pitches), np.std(pitches)]
+        }
+        
+        # Flatten all feature arrays into a single list
+        feature_vector = []
+        for value in features.values():
+            feature_vector.extend(value)
+        
+        print(f"✅ Features successfully extracted and formatted (Total: {len(feature_vector)} features)")
+        return feature_vector
+    except Exception as e:
+        print(f"❌ Error extracting features from {file_path}: {e}")
+        return None

models/feature_list.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89684fc58e221ad3db3297bb778f0d6e2e29a3a9cebf2aeadbb8b259dfde5db4
+size 1050

models/gender_model_lr.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f41099b986d8c0257fb683b11ffd362db279a856050c1cc5f0a41affbbbe63e
+size 1300

models/gender_model_rf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b176461a30fd2ff9aa512efe5c47c0e68e8c98eced4f11361543dbc01625042
+size 8615017

models/gender_model_svm.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63369fa0c52524cfe50643a330f4689eeca01b0073c9d035e1c4ef04c37608e
+size 1050972

models/scaler_gender_model_lr.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53dddf6e8eb645af405c4329c6cdbec249dff72cd1b747756b8808dad8ded445
+size 3451

models/scaler_gender_model_rf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53dddf6e8eb645af405c4329c6cdbec249dff72cd1b747756b8808dad8ded445
+size 3451

models/scaler_gender_model_svm.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53dddf6e8eb645af405c4329c6cdbec249dff72cd1b747756b8808dad8ded445
+size 3451

requirements.txt

@@ -0,0 +1,9 @@
+flask
+flask-cors
+numpy
+librosa
+joblib
+scikit-learn
+soundfile
+praat-parselmouth
+scipy

static/script.js

@@ -0,0 +1,134 @@
+const API_URL = 'http://localhost:5000';
+
+// Page Navigation
+function showPage(pageId) {
+    document.querySelectorAll('.page').forEach(page => page.classList.add('hidden'));
+    document.getElementById(pageId).classList.remove('hidden');
+}
+
+// Drag & Drop Handling
+const dropZone = document.getElementById('drop-zone');
+const fileInput = document.getElementById('file-input');
+const analyzeBtn = document.getElementById('analyze-btn');
+const audioPlayback = document.getElementById('audio-playback');
+let audioFile = null;
+
+dropZone.addEventListener('dragover', (e) => {
+    e.preventDefault();
+    dropZone.classList.add('drag-over');
+});
+
+dropZone.addEventListener('dragleave', () => {
+    dropZone.classList.remove('drag-over');
+});
+
+dropZone.addEventListener('drop', (e) => {
+    e.preventDefault();
+    dropZone.classList.remove('drag-over');
+
+    if (e.dataTransfer.files.length > 0) {
+        handleFile(e.dataTransfer.files[0]);
+    }
+});
+
+fileInput.addEventListener('change', (e) => {
+    handleFile(e.target.files[0]);
+});
+
+function handleFile(file) {
+    if (file && file.type.startsWith('audio/')) {
+        audioFile = file;
+        analyzeBtn.disabled = false;
+        audioPlayback.src = URL.createObjectURL(file);
+        audioPlayback.classList.remove('hidden');
+    } else {
+        showError('Please upload a valid audio file');
+    }
+}
+
+// Voice Recording
+let mediaRecorder;
+let audioChunks = [];
+const recordBtn = document.getElementById('record-btn');
+const recordingStatus = document.getElementById('recording-status');
+
+recordBtn.addEventListener('click', async () => {
+    try {
+        if (recordBtn.textContent === '🎤 Record Voice') {
+            const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+            mediaRecorder = new MediaRecorder(stream);
+            audioChunks = [];
+            
+            mediaRecorder.ondataavailable = (e) => {
+                audioChunks.push(e.data);
+            };
+
+            mediaRecorder.onstop = () => {
+                audioFile = new Blob(audioChunks, { type: 'audio/wav' });
+                analyzeBtn.disabled = false;
+                audioPlayback.src = URL.createObjectURL(audioFile);
+                audioPlayback.classList.remove('hidden');
+                recordingStatus.textContent = 'Recording saved!';
+            };
+
+            mediaRecorder.start();
+            recordBtn.textContent = '⏹ Stop Recording';
+            recordingStatus.textContent = 'Recording...';
+        } else {
+            mediaRecorder.stop();
+            recordBtn.textContent = '🎤 Record Voice';
+        }
+    } catch (error) {
+        showError('Unable to access microphone');
+    }
+});
+
+// Processing & Prediction
+analyzeBtn.addEventListener('click', async () => {
+    showPage('processing-page');
+    const progressBar = document.getElementById('progress-bar');
+
+    try {
+        const formData = new FormData();
+        formData.append('audio', audioFile, "recorded_audio.wav");
+
+        const response = await fetch(`${API_URL}/predict`, {
+            method: 'POST',
+            body: formData
+        });
+
+        if (!response.ok) throw new Error('Prediction failed');
+
+        const results = await response.json();
+        progressBar.style.width = '100%';
+        displayResults(results);
+    } catch (error) {
+        showError('Analysis failed. Please try again.');
+    }
+});
+
+function displayResults(results) {
+    document.getElementById('age-result').textContent = results.age_group;
+    document.getElementById('gender-result').textContent = results.gender;
+    showPage('results-page');
+}
+
+function showError(message) {
+    document.getElementById('error-message').textContent = message;
+    showPage('error-page');
+}
+
+function downloadReport() {
+    const results = {
+        age: document.getElementById('age-result').textContent,
+        gender: document.getElementById('gender-result').textContent,
+        timestamp: new Date().toISOString()
+    };
+
+    const blob = new Blob([JSON.stringify(results, null, 2)], { type: 'application/json' });
+    const url = URL.createObjectURL(blob);
+    const a = document.createElement('a');
+    a.href = url;
+    a.download = 'voice-analysis-report.json';
+    a.click();
+}

static/styles.css

@@ -0,0 +1,153 @@
+/* Color Theme */
+:root {
+    --primary-color: #008080; /* Teal */
+    --secondary-color: #005f5f;
+    --error-color: #f44336;
+}
+
+/* Reset & Base Styles */
+body {
+    font-family: 'Arial', sans-serif;
+    margin: 0;
+    padding: 0;
+    background-color: #f0f8f8;
+}
+
+/* Sticky Header */
+.sticky-header {
+    position: sticky;
+    top: 0;
+    background-color: var(--primary-color);
+    color: white;
+    padding: 10px 20px;
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
+    z-index: 1000;
+}
+
+.sticky-header h1 {
+    margin: 0;
+    font-size: 20px;
+}
+
+.sticky-header nav ul {
+    list-style: none;
+    margin: 0;
+    padding: 0;
+    display: flex;
+}
+
+.sticky-header nav ul li {
+    margin: 0 10px;
+}
+
+.sticky-header nav ul li a {
+    color: white;
+    text-decoration: none;
+    font-weight: bold;
+}
+
+.sticky-header nav ul li a:hover {
+    text-decoration: underline;
+}
+
+/* Page Layout */
+.page {
+    max-width: 800px;
+    margin: 50px auto;
+    padding: 20px;
+    background: white;
+    border-radius: 8px;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+}
+
+/* Hidden Pages */
+.hidden {
+    display: none;
+}
+
+/* Upload Section */
+.upload-container {
+    border: 2px dashed var(--primary-color);
+    padding: 20px;
+    text-align: center;
+    margin: 20px 0;
+    cursor: pointer;
+    transition: all 0.3s ease;
+}
+
+.upload-container.drag-over {
+    background: rgba(0, 128, 128, 0.1);
+}
+
+/* Progress Bar */
+.progress-container {
+    width: 100%;
+    height: 20px;
+    background-color: #f0f0f0;
+    border-radius: 10px;
+    overflow: hidden;
+    margin: 20px 0;
+}
+
+.progress-bar {
+    width: 0%;
+    height: 100%;
+    background-color: var(--primary-color);
+    transition: width 0.3s ease;
+}
+
+/* Results */
+.results-container {
+    display: flex;
+    justify-content: space-around;
+    margin: 20px 0;
+}
+
+.result-card {
+    padding: 20px;
+    border: 1px solid #ddd;
+    border-radius: 8px;
+    text-align: center;
+    background: #e0f7f7;
+    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
+}
+
+/* Buttons */
+button {
+    padding: 10px 20px;
+    border: none;
+    border-radius: 4px;
+    background-color: var(--primary-color);
+    color: white;
+    cursor: pointer;
+    transition: background-color 0.3s;
+    font-size: 16px;
+}
+
+button:hover {
+    background-color: var(--secondary-color);
+}
+
+button:disabled {
+    background-color: #cccccc;
+    cursor: not-allowed;
+}
+
+/* Charts */
+.charts-container {
+    display: flex;
+    flex-wrap: wrap;
+    justify-content: space-around;
+    gap: 20px;
+    margin: 20px 0;
+}
+
+.chart-wrapper {
+    background: white;
+    padding: 15px;
+    border-radius: 8px;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+}

templates/index.html

@@ -0,0 +1,81 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8" />
+  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+  <title>Voice Age & Gender Predictor</title>
+  <link rel="stylesheet" href="{{ url_for('static', filename='styles.css') }}" />
+  <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
+</head>
+<body>
+
+  <!-- Header -->
+  <header class="sticky-header">
+    <h1>Voice Age & Gender Predictor</h1>
+    <nav>
+      <ul>
+        <li><a href="#" onclick="showPage('landing-page')">Home</a></li>
+        <li><a href="#" onclick="showPage('upload-page')">Upload</a></li>
+        <li><a href="#" onclick="showPage('results-page')">Results</a></li>
+      </ul>
+    </nav>
+  </header>
+
+  <!-- Landing Page -->
+  <div class="page" id="landing-page">
+    <h2>Discover Your Voice Characteristics</h2>
+    <p>Analyze your voice with AI technology.</p>
+    <button onclick="showPage('upload-page')">Start Analysis</button>
+  </div>
+
+  <!-- Upload Page -->
+  <div class="page hidden" id="upload-page">
+    <h2>Upload or Record Audio</h2>
+    <div class="upload-container" id="drop-zone">
+      <input type="file" id="file-input" accept="audio/*" />
+      <p>Drag & Drop or Click to Upload</p>
+    </div>
+    <div class="record-container">
+      <button id="record-btn">🎤 Record Voice</button>
+      <div id="recording-status"></div>
+      <audio id="audio-playback" controls class="hidden"></audio>
+    </div>
+    <button id="analyze-btn" disabled>Analyze Voice</button>
+  </div>
+
+  <!-- Processing Page -->
+  <div class="page hidden" id="processing-page">
+    <h2>Processing Audio...</h2>
+    <div class="progress-container">
+      <div class="progress-bar" id="progress-bar"></div>
+    </div>
+    <p id="processing-status">Analyzing your voice...</p>
+  </div>
+
+  <!-- Results Page -->
+  <div class="page hidden" id="results-page">
+    <h2>Analysis Results</h2>
+    <div class="results-container">
+      <div class="result-card">
+        <h3>Predicted Age</h3>
+        <p id="age-result"></p>
+      </div>
+      <div class="result-card">
+        <h3>Predicted Gender</h3>
+        <p id="gender-result"></p>
+      </div>
+    </div>
+    <div class="charts-container">
+      <canvas id="confidence-chart"></canvas>
+      <canvas id="gender-chart"></canvas>
+      <canvas id="age-chart"></canvas>
+    </div>
+    <div class="action-buttons">
+      <button onclick="showPage('upload-page')">🔄 Try Again</button>
+      <button onclick="downloadReport()">📥 Download Report</button>
+    </div>
+  </div>
+
+  <script src="{{ url_for('static', filename='script.js') }}"></script>
+</body>
+</html>