Update app.py

app.py

@@ -4,34 +4,28 @@ import pandas as pd
 import plotly.express as px
 
 # ------------------------------
-# Load pretrained models
+# Load pretrained models (CPU-friendly, public)
 # ------------------------------
 text_classifier = pipeline(
     "text-classification",
-    model="j-hartmann/emotion-english-distilroberta-base",
-    return_all_scores=True
+    model="j-hartmann/emotion-english-distilroberta-base",  # public
+    top_k=None,   # replaces deprecated return_all_scores
+    device=-1
 )
 
 audio_classifier = pipeline(
     "audio-classification",
-    model="superb/wav2vec2-base-superb-er"
+    model="superb/wav2vec2-base-superb-er",  # public model
+    device=-1
 )
 
 # ------------------------------
 # Map emotion to emoji
 # ------------------------------
 EMOJI_MAP = {
-    "anger": "😡",
-    "disgust": "🤢",
-    "fear": "😨",
-    "joy": "😄",
-    "neutral": "😐",
-    "sadness": "😢",
-    "surprise": "😲",
-    "hap": "😄",  # for audio model
-    "neu": "😐",
-    "sad": "😢",
-    "ang": "😡"
+    "anger": "😡", "disgust": "🤢", "fear": "😨", "joy": "😄",
+    "neutral": "😐", "sadness": "😢", "surprise": "😲",
+    "hap": "😄", "neu": "😐", "sad": "😢", "ang": "😡"
 }
 
 # ------------------------------
@@ -82,44 +76,38 @@ def make_bar_chart(scores_dict, title="Emotion Scores"):
 def predict(text, audio, w_text, w_audio):
     text_preds, audio_preds = None, None
     if text:
-        text_preds = text_classifier(text)[0]
+        text_preds = text_classifier(text)
     if audio:
         audio_preds = audio_classifier(audio)
     fused = fuse_predictions(text_preds, audio_preds, w_text, w_audio)
 
-    # Display final predicted emotion with emoji
+    # 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']})"
 
-    # Bar charts
-    charts = []
-    if text_preds:
-        charts.append(make_bar_chart({p['label']: p['score'] for p in text_preds}, "Text Emotion Scores"))
-    if audio_preds:
-        charts.append(make_bar_chart({p['label']: p['score'] for p in audio_preds}, "Audio Emotion Scores"))
-    charts.append(make_bar_chart(fused['all_scores'], "Fused Emotion Scores"))
+    # Only show fused chart to avoid Gradio multiple output issues
+    chart = make_bar_chart(fused['all_scores'], "Fused Emotion Scores")
 
-    return final_emotion, charts
+    return final_emotion, chart
 
 # ------------------------------
-# Build Gradio interface
+# Gradio Interface
 # ------------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("## 🎭 Multimodal Emotion Classification (Text + Speech)")
+    gr.Markdown("## 🎭 Public CPU-Friendly Multimodal Emotion Classifier")
 
     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)")
+            w1 = gr.Slider(minimum=0.0, maximum=1.0, value=0.5, label="Text weight")
+            w2 = gr.Slider(minimum=0.0, maximum=1.0, value=0.5, label="Audio weight")
             btn = gr.Button("Predict")
         with gr.Column():
-            final_label = gr.Markdown(label="Predicted Emotion")
-            chart_output = gr.Plot(label="Emotion Scores")
+            final_label = gr.Markdown()
+            chart_output = gr.Plot()
 
-    # Button click triggers prediction
     btn.click(fn=predict, inputs=[txt, aud, w1, w2], outputs=[final_label, chart_output])
 
-demo.launch()
+demo.launch()