Update app.py

app.py

@@ -1,19 +1,20 @@
 import streamlit as st
 import tensorflow as tf
 import numpy as np
-from tensorflow.keras.preprocessing.image import load_img, img_to_array
+from tensorflow.keras.preprocessing.image import img_to_array
 from PIL import Image
 from gtts import gTTS
 import tempfile
+import base64
 
 # Load the trained model
 MODEL_PATH = "image_model.h5"
 model = tf.keras.models.load_model(MODEL_PATH)
 
-# Define image dimensions
+# Image dimensions
 IMG_WIDTH, IMG_HEIGHT = 64, 48
 
-# Class labels with descriptions
+# Class labels
 CLASS_LABELS = {
     0: "Normal driving (safe)",
     1: "Texting - right",
@@ -28,50 +29,43 @@ CLASS_LABELS = {
 }
 
 def predict_image(image):
-    # Preprocess the image
     img_array = img_to_array(image)
-    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
-    img_array = img_array / 255.0  # Normalize pixel values to [0, 1]
-
-    # Make a prediction
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = img_array / 255.0
     predictions = model.predict(img_array)
     predicted_class = np.argmax(predictions, axis=1)[0]
     confidence = np.max(predictions)
-
     return CLASS_LABELS[predicted_class], confidence
 
-def speak(text):
-    # Generate speech using gTTS
+def speak_auto(text):
     tts = gTTS(text=text, lang='en')
-    # Save the audio file in a temporary location
-    with tempfile.NamedTemporaryFile(delete=False, suffix='.mp3') as tmpfile:
-        tmpfile_path = tmpfile.name
-        tts.save(tmpfile_path)
-        # Return the path of the temporary file so Streamlit can play it
-        return tmpfile_path
+    with tempfile.NamedTemporaryFile(delete=True, suffix=".mp3") as fp:
+        tts.save(fp.name)
+        audio_bytes = fp.read()
+        b64 = base64.b64encode(audio_bytes).decode()
+        audio_html = f"""
+            <audio autoplay>
+                <source src="data:audio/mp3;base64,{b64}" type="audio/mp3">
+            </audio>
+        """
+        st.markdown(audio_html, unsafe_allow_html=True)
 
 # Streamlit app
 st.title("Driver Distraction Detection")
 st.markdown("Team18 Image Project : Sayandip Bhattacharyya, Purnendu Rudrapal, Sridatta Das, Sidhartha Karjee")
 
-# File upload
 uploaded_file = st.file_uploader("Choose an image file", type=["jpg", "jpeg", "png"])
 
 if uploaded_file is not None:
-    # Display the uploaded image
     image = Image.open(uploaded_file).convert("RGB")
     resized_image = image.resize((IMG_WIDTH, IMG_HEIGHT))
     st.image(image, caption="Uploaded Image", use_container_width=True)
 
-    # Predict the class
     with st.spinner("Predicting..."):
         predicted_class, confidence = predict_image(resized_image)
 
-    # Display the result
-    prediction_text = f"Class: {predicted_class}\nConfidence: {confidence:.2%}"
+    prediction_text = f"{predicted_class}. Confidence: {confidence:.2%}"
     st.subheader("Prediction")
     st.write(prediction_text)
 
-    # Generate and play the audio
-    audio_path = speak(prediction_text)
-    st.audio(audio_path, format="audio/mp3")
+    speak_auto(prediction_text)  # Auto-play speech