Update app.py

app.py

@@ -4,7 +4,7 @@ import pandas as pd
 import plotly.express as px
 
 # ------------------------------
-# Load pretrained models (CPU-friendly)
+# Load pretrained text model
 # ------------------------------
 text_classifier = pipeline(
     "text-classification",
@@ -12,12 +12,6 @@ text_classifier = pipeline(
     top_k=None  # returns all scores
 )
 
-# Use a small, public audio model
-audio_classifier = pipeline(
-    "audio-classification",
-    model="superb/wav2vec2-small-superb-er"  # small model
-)
-
 # ------------------------------
 # Map emotion to emoji
 # ------------------------------
@@ -28,42 +22,11 @@ EMOJI_MAP = {
     "joy": "😄",
     "neutral": "😐",
     "sadness": "😢",
-    "surprise": "😲",
-    "hap": "😄",  # audio model labels
-    "neu": "😐",
-    "sad": "😢",
-    "ang": "😡"
+    "surprise": "😲"
 }
 
 # ------------------------------
-# Fusion function
-# ------------------------------
-def fuse_predictions(text_preds=None, audio_preds=None, w_text=0.5, w_audio=0.5):
-    labels = set()
-    if text_preds:
-        labels |= {p['label'] for p in text_preds}
-    if audio_preds:
-        labels |= {p['label'] for p in audio_preds}
-    scores = {l: 0.0 for l in labels}
-
-    def normalize(preds):
-        total = sum(p['score'] for p in preds)
-        return {p['label']: p['score']/total for p in preds}
-
-    if text_preds:
-        t_norm = normalize(text_preds)
-        for l in labels:
-            scores[l] += w_text * t_norm.get(l, 0)
-    if audio_preds:
-        a_norm = normalize(audio_preds)
-        for l in labels:
-            scores[l] += w_audio * a_norm.get(l, 0)
-
-    best = max(scores.items(), key=lambda x: x[1]) if scores else ("none", 0)
-    return {"fused_label": best[0], "fused_score": round(best[1], 3), "all_scores": scores}
-
-# ------------------------------
-# Bar chart function
+# Create bar chart
 # ------------------------------
 def make_bar_chart(scores_dict, title="Emotion Scores"):
     df = pd.DataFrame({
@@ -80,41 +43,45 @@ def make_bar_chart(scores_dict, title="Emotion Scores"):
 # ------------------------------
 # Prediction function
 # ------------------------------
-def predict(text, audio, w_text, w_audio):
-    text_preds, audio_preds = None, None
-    if text:
-        text_preds = text_classifier(text)  # list of dicts
-    if audio:
-        audio_preds = audio_classifier(audio)  # list of dicts
-
-    fused = fuse_predictions(text_preds, audio_preds, w_text, w_audio)
-
-    # Final emotion with emoji
-    label = fused['fused_label']
-    emoji = EMOJI_MAP.get(label, "")
-    final_emotion = f"### Final Predicted Emotion: {label.upper()} {emoji} (score: {fused['fused_score']})"
-
-    # Fused bar chart
-    chart = make_bar_chart(fused['all_scores'], "Fused Emotion Scores")
-    return final_emotion, chart
+def predict(text, w_text=1.0):
+    if not text:
+        return "Please enter text.", None
+    preds = text_classifier(text)[0]  # get all scores
+    scores = {p['label']: p['score'] for p in preds}
+    best_label = max(scores, key=scores.get)
+    emoji = EMOJI_MAP.get(best_label, "")
+    
+    # Animate emoji with simple bouncing
+    final_emotion_html = f"""
+    <div style="font-size:80px; text-align:center; animation: bounce 1s infinite;">
+        {emoji}
+    </div>
+    <h3 style="text-align:center;">{best_label.upper()} (score: {scores[best_label]:.2f})</h3>
+    <style>
+    @keyframes bounce {{
+        0%, 20%, 50%, 80%, 100% {{transform: translateY(0);}}
+        40% {{transform: translateY(-20px);}}
+        60% {{transform: translateY(-10px);}}
+    }}
+    </style>
+    """
+    chart = make_bar_chart(scores, "Text Emotion Scores")
+    return final_emotion_html, chart
 
 # ------------------------------
 # Build Gradio interface
 # ------------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("## 🎭 Multimodal Emotion Classification (Text + Speech)")
+    gr.Markdown("## 🎭 Text Emotion Classification with Emoji Animation")
 
     with gr.Row():
         with gr.Column():
             txt = gr.Textbox(label="Text input", placeholder="Type something emotional...")
-            aud = gr.Audio(type="filepath", label="Upload speech (wav/mp3)")
-            w1 = gr.Slider(minimum=0.0, maximum=1.0, value=0.5, label="Text weight (w_text)")
-            w2 = gr.Slider(minimum=0.0, maximum=1.0, value=0.5, label="Audio weight (w_audio)")
             btn = gr.Button("Predict")
         with gr.Column():
-            final_label = gr.Markdown(label="Predicted Emotion")
-            chart_output = gr.Plot(label="Fused Emotion Scores")
+            final_label = gr.HTML(label="Predicted Emotion")
+            chart_output = gr.Plot(label="Emotion Scores")
 
-    btn.click(fn=predict, inputs=[txt, aud, w1, w2], outputs=[final_label, chart_output])
+    btn.click(fn=predict, inputs=[txt], outputs=[final_label, chart_output])
 
 demo.launch()