Fix: Remove Unicode escapes and simplify code for proper Gradio initialization

app.py

@@ -10,24 +10,20 @@ model = None
 tokenized_dataset = None
 
 def load_resources():
-    """Load dataset, tokenizer, and model on demand"""
     global dataset, tokenizer, model, tokenized_dataset
     
     if dataset is not None:
         return
     
-    # Load the Arabic sentiment dataset
     try:
         dataset = load_dataset('arbml/Arabic_Sentiment_Twitter_Corpus')
     except:
         dataset = load_dataset('asas-ai/Arabic_Sentiment_Twitter_Corpus')
     
-    # Load tokenizer and model
     tokenizer = AutoTokenizer.from_pretrained('distilbert-base-multilingual-cased')
     model = AutoModelForSequenceClassification.from_pretrained('distilbert-base-multilingual-cased', num_labels=3)
 
 def preprocess_function(examples):
-    """Tokenize and preprocess examples"""
     text_column = 'tweet' if 'tweet' in examples else 'text'
     encoding = tokenizer(examples[text_column], truncation=True, padding='max_length', max_length=128)
     
@@ -38,11 +34,9 @@ def preprocess_function(examples):
     return encoding
 
 def train_model(epochs, batch_size, learning_rate):
-    """Fine-tune DistilBERT on Arabic sentiment dataset (Saudi dialect)"""
     try:
         load_resources()
         
-        # Preprocess dataset if not already done
         global tokenized_dataset
         if tokenized_dataset is None:
             tokenized_dataset = dataset.map(preprocess_function, batched=True, remove_columns=dataset['train'].column_names)
@@ -65,53 +59,45 @@ def train_model(epochs, batch_size, learning_rate):
             eval_dataset=tokenized_dataset.get('validation', tokenized_dataset['train']),
         )
         
-        # Start training
         trainer.train()
         
-        return f"\u270d\u2705 \u062a\u0645 \u0627\u0644\u062a\u062f\u0631\u064a\u0628 \u0628\u0646\u062c\u0627\u062d!\n\u0627\u0644\u0646\u0645\u0648\u0630\u062c \u0645\u062d\u0641\u0648\u0638 \u0641\u064a ./results\n\u0645\u0639\u062f\u0644 \u0627\u0644\u062a\u0639\u0644\u0645: {learning_rate}\n\u0639\u062f\u062f \u0627\u0644\u062d\u0642\u0628: {epochs}\nBatch Size: {batch_size}"
+        return f"Training completed successfully! Model saved in ./results"
     except Exception as e:
-        return f"\u274c \u062e\u0637\u0623 \u0623\u062b\u0646\u0627\u0621 \u0627\u0644\u062a\u062f\u0631\u064a\u0628: {str(e)}"
+        return f"Error during training: {str(e)}"
 
-# Create Gradio interface
 with gr.Blocks(title="DistilBERT Arabic Sentiment Training") as demo:
-    gr.Markdown("""
-# \ud83d\ude80 \u062a\u062f\u0631\u064a\u0628 \u0646\u0645\u0648\u0630\u062c DistilBERT \u0627\u0644\u0639\u0631\u0628\u064a
-
-\u0636\u0628\u0637 \u0646\u0645\u0648\u0630\u062c **DistilBERT** \u0639\u0644\u0649 \u062a\u062d\u0644\u064a\u0644 \u0627\u0644\u0645\u0634\u0627\u0639\u0631 \u0628\u0627\u0644\u0644\u063a\u0629 \u0627\u0644\u0639\u0631\u0628\u064a\u0629 (\u0627\u0644\u0644\u0647\u062c\u0629 \u0627\u0644\u0633\u0639\u0648\u062f\u064a\u0629)
-
-### \u0645\u0639\u0644\u0648\u0645\u0627\u062a \u0627\u0644\u0646\u0645\u0648\u0630\u062c:
-- **\u0627\u0644\u0646\u0645\u0648\u0630\u062c \u0627\u0644\u0623\u0633\u0627\u0633\u064a**: distilbert-base-multilingual-cased (67M \u0645\u0639\u0627\u0645\u0644)
-- **\u0627\u0644\u0645\u0647\u0645\u0629**: \u062a\u0635\u0646\u064a\u0641 \u0627\u0644\u0646\u0635\u0648\u0635 (\u0627\u0644\u0645\u062a\u0639\u062f \u0627\u0644\u0644\u063a\u0627\u062a)
-- **\u0642\u0627\u0639\u062f\u0629 \u0627\u0644\u0628\u064a\u0627\u0646\u0627\u062a**: arbml/Arabic_Sentiment_Twitter_Corpus (58.8k \u0645\u062b\u0627\u0644)
-- **\u0627\u0644\u0644\u063a\u0629**: \u0627\u0644\u0639\u0631\u0628\u064a\u0629 (\u0627\u0644\u0644\u0647\u062c\u0629 \u0627\u0644\u0633\u0639\u0648\u062f\u064a\u0629 \u0648\u0627\u0644\u062e\u0644\u064a\u062c\u064a\u0629)
-""")
+    gr.Markdown("# DistilBERT Arabic Sentiment Training")
+    gr.Markdown("Fine-tune DistilBERT on Arabic sentiment analysis (Saudi dialect)")
+    
+    gr.Markdown("### Model Information:")
+    gr.Markdown("- **Base Model**: distilbert-base-multilingual-cased (67M parameters)")
+    gr.Markdown("- **Task**: Text Classification (Multilingual)")
+    gr.Markdown("- **Dataset**: arbml/Arabic_Sentiment_Twitter_Corpus (58.8k examples)")
+    gr.Markdown("- **Language**: Arabic (Saudi & Gulf dialects)")
     
     with gr.Row():
         with gr.Column():
-            gr.Markdown("### \u0625\u0639\u062f\u0627\u062f\u0627\u062a \u0627\u0644\u062a\u062f\u0631\u064a\u0628")
-            epochs = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="\u0639\u062f\u062f \u0627\u0644\u062d\u0642\u0628 (Epochs)")
+            gr.Markdown("### Training Settings")
+            epochs = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="Epochs")
             batch_size = gr.Slider(minimum=8, maximum=64, value=32, step=8, label="Batch Size")
             learning_rate = gr.Slider(minimum=1e-5, maximum=1e-3, value=2e-5, step=1e-5, label="Learning Rate")
         
         with gr.Column():
-            gr.Markdown("### \u062d\u0627\u0644\u0629 \u0627\u0644\u062a\u062f\u0631\u064a\u0628")
-            output_text = gr.Textbox(label="\u0627\u0644\u0645\u062e\u0631\u062c\u0627\u062a", lines=10, interactive=False)
+            gr.Markdown("### Training Status")
+            output_text = gr.Textbox(label="Output", lines=10, interactive=False)
     
-    train_button = gr.Button("\ud83d\udd25 \u0628\u062f\u0621 \u0627\u0644\u062a\u062f\u0631\u064a\u0628", variant="primary", scale=2)
+    train_button = gr.Button("Start Training", variant="primary")
     train_button.click(
         fn=train_model,
         inputs=[epochs, batch_size, learning_rate],
         outputs=output_text
     )
     
-    gr.Markdown("""
-### \u062a\u0641\u0627\u0635\u064a\u0644 \u0627\u0644\u062a\u062f\u0631\u064a\u0628:
-- **\u0645\u0631\u062d\u0644\u0629 \u0627\u0644\u0628\u0646\u0627\u0621**: GPU \u0645\u062c\u0627\u0646\u064a (\u0645\u0628\u0627\u0634\u0631 \u0639\u0628\u0631 Hugging Face Spaces)
-- **\u0648\u0642\u062a \u0627\u0644\u062a\u062d\u0645\u064a\u0644**: 5-10 \u062f\u0642\u0627\u0626\u0642 (GPU) \u0623\u0648 15-20 \u062f\u0642\u064a\u0642\u0629 (CPU)
-- **\u0648\u0642\u062a \u0627\u0644\u062a\u062f\u0631\u064a\u0628**: \u064a\u0639\u062a\u0645\u062f \u0639\u0644\u0649 \u0639\u062f\u062f \u0627\u0644\u062d\u0642\u0628 \u0648Batch Size
-- **\u0645\u062e\u0631\u062c\u0627\u062a \u0627\u0644\u0646\u0645\u0648\u0630\u062c**: \u0645\u062d\u0641\u0648\u0638 \u0639\u0646\u062f ./results
-- **\u0627\u0644\u0627\u0633\u062a\u062e\u062f\u0627\u0645**: \u0627\u0644\u0646\u0635\u0648\u0635 \u0627\u0644\u0639\u0631\u0628\u064a\u0629 \u0641\u0642\u0637
-""")
+    gr.Markdown("### Training Details:")
+    gr.Markdown("- **Hardware**: Free GPU (Hugging Face Spaces)")
+    gr.Markdown("- **Expected Time**: 5-10 minutes (GPU) or 15-20 minutes (CPU)")
+    gr.Markdown("- **Output Directory**: ./results")
+    gr.Markdown("- **Usage**: Arabic text only")
 
 if __name__ == "__main__":
     demo.launch()