Update app.py

app.py

@@ -9,22 +9,19 @@ from huggingface_hub import hf_hub_download
 
 REPO_ID = "anggars/neural-mathrock"
 
-# 1. Download model dan label terbaru dari repo
+# Load model and labels
 model_path = hf_hub_download(repo_id=REPO_ID, filename="neural_mathrock_model.keras")
 label_path = hf_hub_download(repo_id=REPO_ID, filename="neural_mathrock_labels.pkl")
 
-# 2. Load model dan kamus
 model = tf.keras.models.load_model(model_path)
 with open(label_path, 'rb') as f:
     labels = pickle.load(f)
 
-# 3. Fungsi prediksi
 def predict_audio(audio_path):
     if audio_path is None:
-        return {"error": "Upload file audionya dulu."}
+        return {"error": "Please upload an audio file first."}
     
     try:
-        # Preprocessing audio ke spectrogram
         y, sr = librosa.load(audio_path, sr=22050, duration=3.0)
         y = librosa.util.fix_length(y, size=3*22050)
         spec = librosa.feature.melspectrogram(y=y, sr=sr, n_mels=128)
@@ -34,10 +31,8 @@ def predict_audio(audio_path):
         img_rgb = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
         input_tensor = np.expand_dims(img_rgb.astype(np.float32) / 255.0, axis=0)
 
-        # Prediksi
         preds = model.predict(input_tensor, verbose=0)
         
-        # Mapping hasil ke teks pake kamus
         return {
             "mbti": str(labels['mbti'][np.argmax(preds[0])]),
             "emotion": str(labels['emotion'][np.argmax(preds[1])]),
@@ -48,13 +43,12 @@ def predict_audio(audio_path):
     except Exception as e:
         return {"error": str(e)}
 
-# 4. UI Gradio
 demo = gr.Interface(
     fn=predict_audio,
-    inputs=gr.Audio(type="filepath", label="Upload Lagu Math Rock / Midwest Emo"),
-    outputs=gr.JSON(label="Hasil Prediksi"),
+    inputs=gr.Audio(type="filepath", label="Upload Math Rock / Midwest Emo Audio"),
+    outputs=gr.JSON(label="Classification Results"),
     title="Neural Mathrock Classifier"
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(ssr_mode=False)