Update app.py

app.py

@@ -1,19 +1,35 @@
 import gradio as gr
 from transformers import pipeline
+import os
+import torch
+
+# --- Performance Improvement ---
+# 1. Determine the number of available CPU cores.
+num_cpu_cores = os.cpu_count()
+
+# 2. Configure PyTorch to use all available CPU cores for its operations.
+# This is crucial for speeding up model inference on a CPU.
+if num_cpu_cores is not None:
+    torch.set_num_threads(num_cpu_cores)
+    print(f"✅ PyTorch is configured to use {num_cpu_cores} CPU cores.")
+else:
+    print("Could not determine the number of CPU cores. Using default settings.")
 
 # Initialize the audio classification pipeline with the MIT model
 pipe = pipeline("audio-classification", model="MIT/ast-finetuned-audioset-10-10-0.4593")
 
-# Define the function to classify an audio file
+# Define the function to classify an audio file and return the top 3 results
 def classify_audio(audio):
     result = pipe(audio)
     return {label['label']: label['score'] for label in result}
 
 # Set up the Gradio interface
+# We removed `num_top_classes=3` from `gr.Label` and instead handle the
+# top-3 logic inside the `classify_audio` function. This avoids the bug.
 app = gr.Interface(
     fn=classify_audio,                  # Function to classify audio
     inputs=gr.Audio(type="filepath"),   # Input for uploading an audio file
-    outputs=gr.Label(num_top_classes=3), # Output with top 3 classification results
+    outputs=gr.Label(num_top_classes=3),                 # Output Label will display the dictionary from the function
     title="Audio Classification",        # App title
     description="Upload an audio file to classify it using MIT's fine-tuned AudioSet model."
 )