Spaces:

Grey3000
/

Voice_Gender_Recognition

Build error

App Files Files Community

Grey3000 commited on Nov 11, 2024

Commit

c564d8b

1 Parent(s): cafaed5

Add application file

Browse files

Files changed (8) hide show

app.py +81 -0
model.h5 +3 -0
requirements.txt +0 -0
runtime.txt +1 -0
scaler.pkl +3 -0
templates/.gitkeep +0 -0
templates/index.html +113 -0
templates/style.css +54 -0

app.py ADDED Viewed

	@@ -0,0 +1,81 @@

+import streamlit as st
+x = st.slider('Select a value')
+st.write(x, 'squared is', x * x)
+# app.py
+import os
+from flask import Flask, request, jsonify, render_template
+import librosa
+import numpy as np
+import tensorflow as tf
+from sklearn.preprocessing import StandardScaler
+import joblib
+app = Flask(__name__)
+# Load the trained model
+model = tf.keras.models.load_model('model.h5')
+# Load the scaler - you'll need to save this during training
+# Add this after your training code:
+# joblib.dump(scaler, 'scaler.pkl')
+scaler = joblib.load('scaler.pkl')
+def extract_features(audio_file):
+    y, sr = librosa.load(audio_file)
+    mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
+    spectral_centroid = librosa.feature.spectral_centroid(y=y, sr=sr)
+    spectral_bandwidth = librosa.feature.spectral_bandwidth(y=y, sr=sr)
+    spectral_rolloff = librosa.feature.spectral_rolloff(y=y, sr=sr)
+    zero_crossing_rate = librosa.feature.zero_crossing_rate(y)
+    features = np.concatenate([
+        np.mean(mfccs, axis=1),
+        [np.mean(spectral_centroid)],
+        [np.mean(spectral_bandwidth)],
+        [np.mean(spectral_rolloff)],
+        [np.mean(zero_crossing_rate)]
+    ])
+    return features.reshape(1, -1)
+@app.route('/')
+def home():
+    return render_template('index.html')
+@app.route('/predict', methods=['POST'])
+def predict():
+    try:
+        if 'file' not in request.files:
+            return jsonify({'error': 'No file provided'}), 400
+        file = request.files['file']
+        if file.filename == '':
+            return jsonify({'error': 'No file selected'}), 400
+        if not file.filename.endswith('.wav'):
+            return jsonify({'error': 'Please upload a WAV file'}), 400
+        # Extract features
+        features = extract_features(file)
+        # Scale features
+        scaled_features = scaler.transform(features)
+        # Make prediction
+        prediction = model.predict(scaled_features)
+        gender = "Female" if prediction[0][0] < 0.5 else "Male"
+        confidence = float(prediction[0][0] if prediction[0][0] > 0.5 else 1 - prediction[0][0])
+        return jsonify({
+            'prediction': gender,
+            'confidence': f"{confidence * 100:.2f}%"
+        })
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
+if __name__ == '__main__':
+    app.run(debug=True)

model.h5 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f26461701b89642a4b6b3fdfb4bffef2deddd3d6407fec8f79d081a81038f88c
+size 88880

requirements.txt ADDED Viewed

Binary file (2.13 kB). View file

runtime.txt ADDED Viewed

	@@ -0,0 +1 @@


1	+ python-3.9.9

scaler.pkl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:741e3f3a3b430bcfd7e6d3cf285a740b5efa7587ba17d4e24728fdb7762ae826
+size 1567

templates/.gitkeep ADDED Viewed

File without changes

templates/index.html ADDED Viewed

	@@ -0,0 +1,113 @@

+<!-- templates/index.html -->
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Voice Gender Classification</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+</head>
+<body class="bg-gray-100 min-h-screen">
+    <div class="container mx-auto px-4 py-8">
+        <div class="max-w-md mx-auto bg-white rounded-lg shadow-lg p-6">
+            <h1 class="text-2xl font-bold text-center mb-6">Voice Gender Classification</h1>
+            <div class="mb-6">
+                <div class="flex items-center justify-center w-full">
+                    <label class="flex flex-col items-center justify-center w-full h-32 border-2 border-gray-300 border-dashed rounded-lg cursor-pointer bg-gray-50 hover:bg-gray-100">
+                        <div class="flex flex-col items-center justify-center pt-5 pb-6">
+                            <svg class="w-8 h-8 mb-4 text-gray-500" aria-hidden="true" xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 20 16">
+                                <path stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M13 13h3a3 3 0 0 0 0-6h-.025A5.56 5.56 0 0 0 16 6.5 5.5 5.5 0 0 0 5.207 5.021C5.137 5.017 5.071 5 5 5a4 4 0 0 0 0 8h2.167M10 15V6m0 0L8 8m2-2 2 2"/>
+                            </svg>
+                            <p class="mb-2 text-sm text-gray-500"><span class="font-semibold">Click to upload</span> or drag and drop</p>
+                            <p class="text-xs text-gray-500">WAV files only</p>
+                        </div>
+                        <input id="file-upload" type="file" class="hidden" accept=".wav" />
+                    </label>
+                </div>
+            </div>
+            <div id="selected-file" class="mb-4 text-center text-gray-600 hidden">
+                Selected file: <span id="filename"></span>
+            </div>
+            <button id="predict-btn" class="w-full bg-blue-500 text-white py-2 px-4 rounded-lg hover:bg-blue-600 disabled:bg-gray-400 disabled:cursor-not-allowed" disabled>
+                Predict Gender
+            </button>
+            <div id="result" class="mt-6 text-center hidden">
+                <div class="mb-2">
+                    <span class="font-bold">Predicted Gender:</span>
+                    <span id="gender" class="ml-2"></span>
+                </div>
+                <div>
+                    <span class="font-bold">Confidence:</span>
+                    <span id="confidence" class="ml-2"></span>
+                </div>
+            </div>
+            <div id="error" class="mt-4 text-red-500 text-center hidden"></div>
+        </div>
+    </div>
+    <script>
+        const fileUpload = document.getElementById('file-upload');
+        const selectedFile = document.getElementById('selected-file');
+        const filename = document.getElementById('filename');
+        const predictBtn = document.getElementById('predict-btn');
+        const result = document.getElementById('result');
+        const gender = document.getElementById('gender');
+        const confidence = document.getElementById('confidence');
+        const error = document.getElementById('error');
+        fileUpload.addEventListener('change', (e) => {
+            const file = e.target.files[0];
+            if (file) {
+                filename.textContent = file.name;
+                selectedFile.classList.remove('hidden');
+                predictBtn.disabled = false;
+                result.classList.add('hidden');
+                error.classList.add('hidden');
+            }
+        });
+        predictBtn.addEventListener('click', async () => {
+            const file = fileUpload.files[0];
+            if (!file) return;
+            const formData = new FormData();
+            formData.append('file', file);
+            predictBtn.disabled = true;
+            predictBtn.textContent = 'Processing...';
+            try {
+                const response = await fetch('/predict', {
+                    method: 'POST',
+                    body: formData
+                });
+                const data = await response.json();
+                if (response.ok) {
+                    result.classList.remove('hidden');
+                    error.classList.add('hidden');
+                    gender.textContent = data.prediction;
+                    confidence.textContent = data.confidence;
+                } else {
+                    error.textContent = data.error;
+                    error.classList.remove('hidden');
+                    result.classList.add('hidden');
+                }
+            } catch (err) {
+                error.textContent = 'An error occurred while processing the request';
+                error.classList.remove('hidden');
+                result.classList.add('hidden');
+            }
+            predictBtn.disabled = false;
+            predictBtn.textContent = 'Predict Gender';
+        });
+    </script>
+</body>
+</html>

templates/style.css ADDED Viewed

	@@ -0,0 +1,54 @@

+/* Reset some default styles */
+body, html {
+    margin: 0;
+    padding: 0;
+    font-family: Arial, sans-serif;
+  }
+  /* Container styles */
+  .container {
+    max-width: 800px;
+    margin: 0 auto;
+    padding: 2rem;
+  }
+  /* Header styles */
+  h1 {
+    text-align: center;
+    margin-bottom: 2rem;
+  }
+  /* Button styles */
+  button {
+    background-color: #4CAF50;
+    border: none;
+    color: white;
+    padding: 0.75rem 1.5rem;
+    text-align: center;
+    text-decoration: none;
+    display: inline-block;
+    font-size: 16px;
+    margin: 0.5rem;
+    cursor: pointer;
+    border-radius: 4px;
+  }
+  button#record-btn {
+    background-color: #f44336;
+  }
+  button:hover {
+    opacity: 0.8;
+  }
+  /* Status and result styles */
+  #status, #result {
+    margin-top: 1rem;
+    padding: 1rem;
+    border: 1px solid #ccc;
+    border-radius: 4px;
+  }
+  #result {
+    background-color: #f1f1f1;
+  }