Create app.py

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+# Load model and tokenizer
+model_name = "cardiffnlp/twitter-roberta-base-sentiment-latest"
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+def predict_sentiment(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    sentiments = ['Negative', 'Neutral', 'Positive']
+    result = {sentiments[i]: float(predictions[0][i]) for i in range(len(sentiments))}
+    return result
+
+def custom_theme():
+    """Define a custom theme for the Gradio app."""
+    return gr.Theme(
+        # Define your color scheme
+        primary='#FF6347',   
+        text_on_primary='#FFFFFF',  
+        background='#F0F8FF', 
+        card_background='#FAEBD7', 
+        text='#2F4F4F', 
+        icon='light', 
+    )
+
+# Create Gradio interface
+iface = gr.Interface(fn=predict_sentiment,
+                     inputs=gr.inputs.Textbox(lines=2, placeholder="Type your sentence here..."),
+                     outputs=gr.outputs.Label(num_top_classes=3),
+                     theme=custom_theme(),
+                     title="Sentiment Analysis",
+                     description="Analyze the sentiment of your text.",
+                     article="<p style='text-align: center'>Enter a sentence to get its sentiment. The model categorizes sentiments into Negative, Neutral, and Positive.</p>")
+
+if __name__ == "__main__":
+    iface.launch()