Update app.py

app.py

@@ -19,21 +19,23 @@ print("Downloading model and extracting label encoders...")
 model_path = hf_hub_download(repo_id=REPO_ID, filename="model.pt")
 ckpt = torch.load(model_path, map_location=torch.device('cpu'), weights_only=False)
 
-# Petain manual sesuai nama key pas lu nge-save model di PyTorch
+# ── LABEL ENCODER PATCH ──
+class DummyEncoder:
+    def __init__(self, classes_list):
+        self.classes_ = np.array(classes_list)
+
 label_encoders = {
     'mbti': ckpt['le_mbti'],
     'emotion': ckpt['le_emotion'],
-    'vibe': ckpt['le_vibe'],
-    'intensity': ckpt['le_intensity'],
-    'tempo': ckpt['le_tempo']
+    'vibe': DummyEncoder(['Aggressive', 'Atmospheric', 'Melancholic', 'Technical']),
+    'intensity': DummyEncoder(['High', 'Low', 'Medium']),
+    'tempo': DummyEncoder(['Fast', 'Moderate', 'Slow'])
 }
 num_classes = {col: len(le.classes_) for col, le in label_encoders.items()}
 
 # ============================================================
 # ── ARCHITECTURE (WAJIB SESUAIKAN SAMA IPYNB TRAINING LU) ──
 # ============================================================
-# HAPUS DAN GANTI blok arsitektur ini pake class asli lu dari jupyter notebook.
-
 class AudioTransformer(nn.Module):
     def __init__(self):
         super().__init__()
@@ -75,7 +77,6 @@ class MultimodalMathRock(nn.Module):
         x_t = self.text(input_ids, attention_mask)
         fused = self.fusion(torch.cat([x_a, x_t], dim=1))
         return {col: self.heads[col](fused) for col in TARGET_COLS}
-
 # ============================================================
 
 print("Initializing architecture and loading weights...")
@@ -92,14 +93,14 @@ def predict_multimodal(audio_path, lyrics):
         return [None]*5
         
     try:
-        # 1. Load audio mentah (otomatis jadi 16kHz mono)
+        # Load audio mentah (otomatis jadi 16kHz mono)
         y, _ = librosa.load(audio_path, sr=SR, duration=DURATION, mono=True)
         
-        # 2. Ekstraksi fitur pake WavLM processor
+        # Ekstraksi fitur pake WavLM processor
         inputs = audio_processor(y, sampling_rate=SR, return_tensors="pt")
         audio_tensor = inputs.input_values
 
-        # 3. Proses Lirik
+        # Proses Lirik
         if not lyrics or lyrics.strip() == "":
             lyrics = "instrumental"
             
@@ -108,7 +109,7 @@ def predict_multimodal(audio_path, lyrics):
             truncation=True, return_tensors='pt'
         )
         
-        # 4. Forward pass
+        # Forward pass
         with torch.no_grad():
             out = model(audio_tensor, enc['input_ids'], enc['attention_mask'])
             
@@ -128,7 +129,7 @@ def predict_multimodal(audio_path, lyrics):
 
 # ── UI ──
 with gr.Blocks() as demo:
-    gr.Markdown("# Neural Math Rock Classifier")
+    gr.Markdown("# Neural Math Rock & Midwest Emo Classifier")
     gr.Markdown("Multimodal WavLM & XLM-RoBERTa based MBTI and emotion classification system.")
     
     with gr.Row():