Update app.py

app.py

@@ -14,7 +14,7 @@ from huggingface_hub import snapshot_download
 from pydub import AudioSegment
 import noisereduce as nr
 
-
+# 🎨 Apply Custom Dark Mode CSS
 st.markdown(
     """
     <style>
@@ -103,7 +103,8 @@ if uploaded_file:
     # 🎵 Display waveform
     st.markdown("<div class='subheader'>🎼 Audio Waveform:</div>", unsafe_allow_html=True)
     fig, ax = plt.subplots(figsize=(10, 4))
-    librosa.display.waveshow(y, sr=sr, ax=ax)
+    librosa.display.waveshow(y, sr=sr, ax=ax, color="cyan")
+    ax.set_facecolor("#121212")  # Dark background for waveform
     st.pyplot(fig)
 
     # ✅ Noise Reduction
@@ -130,10 +131,29 @@ if uploaded_file:
     st.markdown("<div class='subheader'>📝 Transcribed Text:</div>", unsafe_allow_html=True)
     st.markdown(f"<div class='stMarkdown'>{transcription}</div>", unsafe_allow_html=True)
 
-    # ✅ Emotion Detection
+    # ✅ Emotion Detection (Formatted Output)
     st.markdown("<div class='subheader'>😊 Emotion Analysis:</div>", unsafe_allow_html=True)
+
     emotion_result = emotion_model(file_path)
-    st.write(emotion_result)
+    emotion_labels = {
+        "LABEL_0": "Neutral",
+        "LABEL_1": "Happy",
+        "LABEL_2": "Sad",
+        "LABEL_3": "Angry",
+        "LABEL_4": "Surprised"
+    }
+    top_emotion = max(emotion_result, key=lambda x: x["score"])
+    emotion_name = emotion_labels.get(top_emotion["label"], "Unknown")
+    emotion_score = top_emotion["score"]
+
+    st.markdown(
+        f"""
+        <div style="font-size:24px; color:#4CAF50; font-weight:bold;">
+            {emotion_name} ({emotion_score:.2%} confidence)
+        </div>
+        """,
+        unsafe_allow_html=True
+    )
 
     # ✅ Play Original & Denoised Audio
     st.markdown("<div class='subheader'>🔊 Play Audio:</div>", unsafe_allow_html=True)