Update app.py

app.py

@@ -1,35 +1,30 @@
 import gradio as gr
 import numpy as np
 from PIL import Image
-import librosa
-import matplotlib.pyplot as plt
-import io
 import os
 import random
 from collections import Counter, defaultdict
-from app.model import predict 
-from app.preprocess import preprocess_audio  
+from app.model import predict
+from app.preprocess import preprocess_audio
 
-# Dataset Paths (download manually from Hugging Face)
+# Dataset Paths (download manually from Hugging Face or put in space files)
 AUDIO_DATASET_DIR = "General_Audio_Dataset"
 IMAGE_DATASET_DIR = "Mel_Spectrogram_Images_for_Audio_Classification"
 
-# Get file lists
+# Get file lists safely
 audio_files = [
     os.path.join(AUDIO_DATASET_DIR, f) 
     for f in os.listdir(AUDIO_DATASET_DIR) 
     if f.lower().endswith((".wav", ".mp3"))
-]
+] if os.path.exists(AUDIO_DATASET_DIR) else []
 
 image_files = [
     os.path.join(IMAGE_DATASET_DIR, f) 
     for f in os.listdir(IMAGE_DATASET_DIR) 
     if f.lower().endswith(".png")
-]
+] if os.path.exists(IMAGE_DATASET_DIR) else []
 
-# Helper functions
 def safe_load_image(img):
-    """Ensure input is PIL RGBA image"""
     if img is None:
         return None
     if isinstance(img, np.ndarray):
@@ -37,13 +32,15 @@ def safe_load_image(img):
     img = img.convert("RGBA")
     return img
 
+# Process image
 def process_image_input(img):
     img = safe_load_image(img)
     label, confidence, probs = predict(img)
     return label, round(confidence, 3), probs
 
+# Process audio
 def process_audio_input(audio_path):
-    imgs = preprocess_audio(audio_path)  # returns list of PIL RGBA images
+    imgs = preprocess_audio(audio_path)
     all_preds, all_confs, all_probs = [], [], []
 
     for img in imgs:
@@ -67,16 +64,15 @@ def process_audio_input(audio_path):
         final_label = max(conf_sums, key=conf_sums.get)
 
     final_conf = float(np.mean([all_confs[i] for i, lbl in enumerate(all_preds) if lbl == final_label]))
-
     return final_label, round(final_conf, 3), all_preds, [round(c, 3) for c in all_confs]
 
 # Main classifier
 def classify(audio_path, image, random_audio=False, random_image=False):
-    # Pick random audio
+    # Pick random audio if selected
     if random_audio and audio_files:
         audio_path = random.choice(audio_files)
 
-    # Pick random image
+    # Pick random image if selected
     if random_image and image_files:
         img_path = random.choice(image_files)
         image = Image.open(img_path).convert("RGBA")