Update app.py

app.py

@@ -4,11 +4,10 @@ import numpy as np
 import matplotlib.pyplot as plt
 import gradio as gr
 import soundfile as sf
-from scipy.signal import resample  # Correct resampling method
+from scipy.signal import resample
 
 # Load YAMNet model from TensorFlow Hub
-yamnet_model_handle = "https://tfhub.dev/google/yamnet/1"
-yamnet_model = hub.load(yamnet_model_handle)
+yamnet_model = hub.load("https://tfhub.dev/google/yamnet/1")
 
 # Load class labels
 def load_class_map():
@@ -17,30 +16,30 @@ def load_class_map():
         'https://raw.githubusercontent.com/tensorflow/models/master/research/audioset/yamnet/yamnet_class_map.csv'
     )
     with open(class_map_path, 'r') as f:
-        class_names = [line.strip().split(',')[2] for line in f.readlines()[1:]]
-    return class_names
+        return [line.strip().split(',')[2] for line in f.readlines()[1:]]
 
 class_names = load_class_map()
 
 # Classification function
 def classify_audio(file_path):
     try:
-        # Load audio file (WAV, MP3, etc.)
+        # Load audio
         audio_data, sample_rate = sf.read(file_path)
 
-        # Convert stereo to mono if needed
+        # Convert stereo to mono
         if len(audio_data.shape) > 1:
             audio_data = np.mean(audio_data, axis=1)
 
-        # Normalize audio
+        # Normalize
         audio_data = audio_data / np.max(np.abs(audio_data))
 
-        # Resample to 16kHz if necessary
+        # Resample to 16kHz if needed
         target_rate = 16000
         if sample_rate != target_rate:
             duration = audio_data.shape[0] / sample_rate
             new_length = int(duration * target_rate)
             audio_data = resample(audio_data, new_length)
+            sample_rate = target_rate
 
         # Convert to tensor
         waveform = tf.convert_to_tensor(audio_data, dtype=tf.float32)
@@ -53,20 +52,20 @@ def classify_audio(file_path):
         top_prediction = class_names[top_5[0]]
         top_scores = {class_names[i]: float(mean_scores[i]) for i in top_5}
 
-        # Create waveform plot
+        # Waveform plot
         fig, ax = plt.subplots()
         ax.plot(audio_data)
         ax.set_title("Waveform")
-        ax.set_xlabel("Time")
+        ax.set_xlabel("Time (samples)")
         ax.set_ylabel("Amplitude")
         plt.tight_layout()
 
         return top_prediction, top_scores, fig
 
     except Exception as e:
-        return f"Error processing audio: {e}", {}, None
+        return f"Error processing audio: {str(e)}", {}, None
 
-# Gradio interface
+# Gradio interface (HF-compatible)
 interface = gr.Interface(
     fn=classify_audio,
     inputs=gr.Audio(type="filepath", label="Upload .wav or .mp3 audio file"),
@@ -80,4 +79,4 @@ interface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()