Update app.py

app.py

@@ -4,13 +4,11 @@ import torch
 from transformers import BertTokenizer, AutoModel
 import tensorflow as tf
 
-# Load tokenizer and BERT model for embeddings extraction
 model_name = "aubmindlab/bert-base-arabertv02"
 tokenizer = BertTokenizer.from_pretrained(model_name)
 bert_model = AutoModel.from_pretrained(model_name)
 bert_model.eval()
 
-# Load your trained RNN model
 model = tf.keras.models.load_model("rnn_Bi.h5")
 print("✅ Model loaded successfully!")
 
@@ -29,7 +27,6 @@ def predict_sentiment(text):
     confidence = pred if pred > 0.5 else 1 - pred
     return label, confidence
 
-# Custom CSS for better Arabic support and styling
 css = """
 body {
     font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
@@ -60,28 +57,18 @@ body {
 
 with gr.Blocks(css=css) as iface:
     gr.Markdown("## تحليل المشاعر بالعربية 📝", elem_id="title")
-    gr.Markdown(
-        "أدخل جملة لتحليل المشاعر: هل هي **إيجابية** أم **سلبية**؟",
-        elem_id="description"
-    )
-    text_input = gr.Textbox(
-        lines=3,
-        placeholder="اكتب جملتك هنا...",
-        label="النص"
-    )
+    gr.Markdown("أدخل جملة لتحليل المشاعر: هل هي **إيجابية** أم **سلبية**؟", elem_id="description")
+    text_input = gr.Textbox(lines=3, placeholder="اكتب جملتك هنا...", label="النص")
     predict_btn = gr.Button("تنبؤ")
     sentiment_output = gr.Label(label="النتيجة")
-    confidence_bar = gr.Progress(label="ثقة النموذج")
+    confidence_score = gr.Textbox(label="نسبة الثقة")
 
     def on_predict(text):
         label, confidence = predict_sentiment(text)
-        return label, confidence
+        confidence_percent = f"{confidence*100:.1f}%"
+        return label, confidence_percent
 
-    predict_btn.click(
-        fn=on_predict,
-        inputs=text_input,
-        outputs=[sentiment_output, confidence_bar]
-    )
+    predict_btn.click(fn=on_predict, inputs=text_input, outputs=[sentiment_output, confidence_score])
 
 if __name__ == "__main__":
     iface.launch()