Update app.py

app.py

@@ -121,7 +121,7 @@ interface = gr.Interface(
         gr.Audio(type="filepath", label="Upload Audio (WAV/MP3)"),
         gr.Image(type="pil", label="Upload Spectrogram Image (PNG RGBA Supported)"),
         gr.Checkbox(label="Pick Random Audio from Dataset"),
-        gr.Checkbox(label="Pick Random Image from Dataset"),
+        gr.Checkbox(label="Pick Random Mel Spectrogram Image from Dataset"),
     ],
     outputs=[
         gr.JSON(label="Prediction Results"),
@@ -129,9 +129,13 @@ interface = gr.Interface(
     ],
     title="General Audio Classifier (Audio + Spectrogram Support)",
     description=(
-        "Upload a raw audio file OR a spectrogram image.\n"
-        "You can also select random samples from your Hugging Face datasets.\n"
-        "The output shows a JSON with all details and a separate field for the final label."
+        "\nUpload a raw audio file OR a spectrogram image.\n"
+        "\nYou can also select random samples from your Hugging Face datasets.\n"
+        "\nThe output shows a JSON with all details and a separate field for the final label.\n"
+        "\nYour audio is split into 5-second chunks. Each chunk is converted into a Mel-spectrogram and passed through a CNN trained to recognize patterns in frequency and time. 
+        The model predicts a label for every chunk. 
+        The final result is chosen by majority vote, using confidence scores to break ties. 
+        The output shows the final label, its confidence, and the predictions for each chunk.\n"
     ),
 )