Update app.py

app.py

@@ -4,7 +4,6 @@ import numpy as np
 from tensorflow.keras.preprocessing.image import load_img, img_to_array
 from PIL import Image
 from gtts import gTTS
-import os
 import tempfile
 
 # Load the trained model
@@ -42,11 +41,14 @@ def predict_image(image):
     return CLASS_LABELS[predicted_class], confidence
 
 def speak(text):
+    # Generate speech using gTTS
     tts = gTTS(text=text, lang='en')
-    with tempfile.NamedTemporaryFile(delete=False) as temp_file:
-        temp_file_path = temp_file.name + ".mp3"
-        tts.save(temp_file_path)
-        os.system(f"start {temp_file_path}")  # On Windows, use `start`, on Mac/Linux use `open`
+    # 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
 
 # Streamlit app
 st.title("Driver Distraction Detection")
@@ -66,9 +68,10 @@ if uploaded_file is not None:
         predicted_class, confidence = predict_image(resized_image)
 
     # Display the result
-    st.subheader("Prediction")
     prediction_text = f"Class: {predicted_class}\nConfidence: {confidence:.2%}"
+    st.subheader("Prediction")
     st.write(prediction_text)
 
-    # Speak the prediction
-    speak(prediction_text)
+    # Generate and play the audio
+    audio_path = speak(prediction_text)
+    st.audio(audio_path, format="audio/mp3")