Update app.py

app.py

@@ -1,20 +1,20 @@
 import gradio as gr
 from transformers import pipeline
-import pandas as pd
-import plotly.express as px
 
 # ------------------------------
-# Load pretrained models
+# Load pretrained models (CPU)
 # ------------------------------
 text_classifier = pipeline(
     "text-classification",
     model="j-hartmann/emotion-english-distilroberta-base",
-    return_all_scores=True
+    return_all_scores=True,
+    device=-1  # CPU
 )
 
 audio_classifier = pipeline(
     "audio-classification",
-    model="superb/wav2vec2-base-superb-er"
+    model="m3hrdadfi/wav2vec2-mini-xlsr-emotion",
+    device=-1  # CPU
 )
 
 # ------------------------------
@@ -28,7 +28,7 @@ EMOJI_MAP = {
     "neutral": "😐",
     "sadness": "😢",
     "surprise": "😲",
-    "hap": "😄",  # for audio model
+    "hap": "😄",
     "neu": "😐",
     "sad": "😢",
     "ang": "😡"
@@ -61,21 +61,6 @@ def fuse_predictions(text_preds=None, audio_preds=None, w_text=0.5, w_audio=0.5)
     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}
 
-# ------------------------------
-# Create bar chart
-# ------------------------------
-def make_bar_chart(scores_dict, title="Emotion Scores"):
-    df = pd.DataFrame({
-        "Emotion": list(scores_dict.keys()),
-        "Score": list(scores_dict.values())
-    })
-    fig = px.bar(df, x="Emotion", y="Score", text="Score",
-                 title=title, range_y=[0,1],
-                 color="Emotion", color_discrete_sequence=px.colors.qualitative.Bold)
-    fig.update_traces(texttemplate='%{text:.2f}', textposition='outside')
-    fig.update_layout(yaxis_title="Probability", xaxis_title="Emotion", showlegend=False)
-    return fig
-
 # ------------------------------
 # Prediction function
 # ------------------------------
@@ -92,21 +77,21 @@ def predict(text, audio, w_text, w_audio):
     emoji = EMOJI_MAP.get(label, "")
     final_emotion = f"### Final Predicted Emotion: {label.upper()} {emoji} (score: {fused['fused_score']})"
 
-    # Bar charts
-    charts = []
+    # Simple text-based bar chart
+    chart_text = "\n"
     if text_preds:
-        charts.append(make_bar_chart({p['label']: p['score'] for p in text_preds}, "Text Emotion Scores"))
+        chart_text += "Text scores:\n" + "\n".join([f"{p['label']}: {p['score']:.2f}" for p in text_preds]) + "\n"
     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"))
+        chart_text += "Audio scores:\n" + "\n".join([f"{p['label']}: {p['score']:.2f}" for p in audio_preds]) + "\n"
+    chart_text += "Fused scores:\n" + "\n".join([f"{k}: {v:.2f}" for k,v in fused['all_scores'].items()])
 
-    return final_emotion, charts
+    return final_emotion, chart_text
 
 # ------------------------------
 # Build Gradio interface
 # ------------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("## 🎭 Multimodal Emotion Classification (Text + Speech)")
+    gr.Markdown("## 🎭 CPU-Friendly Multimodal Emotion Classification")
 
     with gr.Row():
         with gr.Column():
@@ -117,9 +102,8 @@ with gr.Blocks() as demo:
             btn = gr.Button("Predict")
         with gr.Column():
             final_label = gr.Markdown(label="Predicted Emotion")
-            chart_output = gr.Plot(label="Emotion Scores")
+            chart_output = gr.Textbox(label="Emotion Scores", interactive=False)
 
-    # Button click triggers prediction
     btn.click(fn=predict, inputs=[txt, aud, w1, w2], outputs=[final_label, chart_output])
 
 demo.launch()