Update app.py

app.py

@@ -1,40 +1,25 @@
 from transformers import pipeline
 import gradio as gr
 
-# Load pre-trained emotion classification model
 model_checkpoint = "MuntasirHossain/RoBERTa-base-finetuned-emotion"
-emotion_model = pipeline("text-classification", model=model_checkpoint)
 
-def classify_and_visualize_emotion(text):
-    # Get the predicted emotion label
-    emotion_label = emotion_model(text)[0]["label"]
-    
-    # Map emotion labels to corresponding emojis
-    emoji_mapping = {
-        "joy": "😄",
-        "sadness": "😢",
-        "love": "❤️",
-        "anger": "😡",
-        "fear": "😱",
-        "surprise": "😲",
-    }
-    
-    # Get the corresponding emoji for the predicted emotion
-    predicted_emoji = emoji_mapping.get(emotion_label, "🤔")
+model = pipeline("text-classification", model=model_checkpoint)
 
-    return f"{emotion_label.capitalize()} {predicted_emoji}"
 
-# Define interface title and description
-title = "Emotion Classifier with Emoji Visualization"
-description = "This AI model classifies text expressions into six emotions: joy, sadness, love, anger, fear, and surprise. The result is visualized with emojis."
+def classify(text):
+    label = model(text)[0]["label"]
+    return label
 
-# Set up Gradio Interface with HTML visualization
-iface = gr.Interface(
-    fn=classify_and_visualize_emotion,
+description = "This AI model is trained to classify texts expressing human emotion into six categories: sadness, joy, love, anger, fear, and surprise." 
+title = "Classify Texts Expressing Emotion"
+# theme = "peach"
+examples=[["This is such a beautiful place"]]
+
+gr.Interface(fn=classify,
     inputs="textbox",
-    outputs=gr.Html(),
+    outputs="text",
     title=title,
+    # theme = theme,
     description=description,
-)
-
-iface.launch()
+    examples=examples,
+).launch()