Upload 2 files

app.py

@@ -0,0 +1,274 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import torch
+import time
+
+print("\n⏳ جاري تحميل نموذج Fine-Tashkeel (الدقيق)...")
+
+model_name = "basharalrfooh/Fine-Tashkeel"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+device = torch.device("cpu")
+model.to(device)
+model.eval()
+
+print(f"✅ جاهز على {device}!\n")
+
+LOADING_HTML = """
+<div style="text-align: center; padding: 2rem;">
+    <div style="display: inline-block; animation: spin 1s linear infinite; font-size: 2.5rem;">⏳</div>
+    <div style="font-size: 1.3rem; color: #667eea; margin-top: 1rem; font-weight: bold;">جاري العمل على التشكيل...</div>
+    <div style="color: #999; margin-top: 0.5rem;">هذا النموذج دقيق وبطيء (20-30 ثانية)، يرجى الانتظار</div>
+</div>
+<style>
+    @keyframes spin {
+        0% { transform: rotate(0deg); }
+        100% { transform: rotate(360deg); }
+    }
+</style>
+"""
+
+def remove_diacritics(text):
+    diacritics = [
+        '\u064B', '\u064C', '\u064D', '\u064E', '\u064F', 
+        '\u0650', '\u0651', '\u0652', '\u0653', '\u0654',
+        '\u0655', '\u0656', '\u0657', '\u0658', '\u0670',
+    ]
+    for diacritic in diacritics:
+        text = text.replace(diacritic, '')
+    return text
+
+def count_diacritics(text):
+    diacritics = [
+        '\u064B', '\u064C', '\u064D', '\u064E', '\u064F', 
+        '\u0650', '\u0651', '\u0652', '\u0653', '\u0654',
+        '\u0655', '\u0656', '\u0657', '\u0658', '\u0670',
+    ]
+    return sum(text.count(d) for d in diacritics)
+
+def run_model(text):
+    if not text or not text.strip():
+        error_msg = "❌ يرجى إدخال نص"
+        stats = {'error': error_msg}
+        return None, None, stats, error_msg
+    
+    try:
+        start = time.time()
+        clean_text = remove_diacritics(text)
+        
+        inputs = tokenizer(
+            clean_text,
+            return_tensors="pt",
+            max_length=1024,
+            truncation=True,
+            padding="max_length"
+        )
+        
+        with torch.no_grad():
+            outputs = model.generate(
+                **inputs,
+                max_length=1024,
+                num_beams=1,
+                early_stopping=True
+            )
+        
+        result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        elapsed = time.time() - start
+        
+        words_count = len(clean_text.split())
+        diacritics_count = count_diacritics(result)
+        speed = round(words_count / elapsed, 1) if elapsed > 0 else 0
+        
+        stats = {
+            "elapsed": elapsed,
+            "words_count": words_count,
+            "chars_count": len(result),
+            "diacritics_count": diacritics_count,
+            "speed": speed
+        }
+        
+        return clean_text, result, stats, "✅ تم التشكيل بنجاح!"
+        
+    except Exception as e:
+        print(f"ERROR: {str(e)}")
+        import traceback
+        traceback.print_exc()
+        error_msg = f"❌ خطأ: {str(e)}"
+        stats = {'error': error_msg}
+        return None, None, stats, error_msg
+
+def generate_final_html(clean_text, result_text, stats, show_comparison, highlight_mode):
+    if not result_text:
+        if stats and 'error' in stats:
+            return f"""
+            <div style="text-align: center; padding: 2rem;">
+                <div style="color: #e74c3c; font-size: 1.2rem;">{stats['error']}</div>
+            </div>
+            """
+        return None
+
+    comparison_html = ""
+    if show_comparison:
+        comparison_html = f"""
+        <div style="display: grid; grid-template-columns: 1fr auto 1fr; gap: 1rem; padding: 1.5rem; background: #f8f9fa; border-radius: 15px; border: 2px solid #ffc107;">
+            <div style="text-align: right;">
+                <h4 style="color: #667eea; margin-bottom: 1rem;">⬅️ قبل التشكيل</h4>
+                <div style="background: white; padding: 1.5rem; border-radius: 10px; border: 2px solid #ddd; font-size: 1.1rem; line-height: 2.2; direction: rtl; text-align: right;">
+                    {clean_text}
+                </div>
+            </div>
+            <div style="display: flex; align-items: center; justify-content: center; font-size: 2rem; color: #667eea;">➡️</div>
+            <div style="text-align: right;">
+                <h4 style="color: #28a745; margin-bottom: 1rem;">➡️ بعد التشكيل</h4>
+                <div style="background: white; padding: 1.5rem; border-radius: 10px; border: 2px solid #28a745; font-size: 1.1rem; line-height: 2.2; direction: rtl; text-align: right;">
+                    {result_text}
+                </div>
+            </div>
+        </div>
+        """
+    
+    highlighted_result = result_text
+    if highlight_mode:
+        diacritics = ['\u064B', '\u064C', '\u064D', '\u064E', '\u064F', 
+                      '\u0650', '\u0651', '\u0652', '\u0653', '\u0654',
+                      '\u0655', '\u0656', '\u0657', '\u0658', '\u0670']
+        for diacritic in diacritics:
+            highlighted_result = highlighted_result.replace(
+                diacritic, 
+                f'<span style="color: #fff; background: #e74c3c; font-weight: bold; padding: 2px 5px; border-radius: 3px; margin: 0 2px;">{diacritic}</span>'
+            )
+    
+    stats_html = f"""
+    <div style="margin-top: 2rem; padding: 1.5rem; background: linear-gradient(135deg, #f8f9fa 0%, #e9ecef 100%); border-radius: 15px;">
+        <h3 style="color: #667eea; text-align: center; margin-bottom: 1.5rem;">📊 إحصائيات التشكيل</h3>
+        <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(140px, 1fr)); gap: 1rem;">
+            <div style="background: white; padding: 1.5rem; border-radius: 12px; text-align: center; box-shadow: 0 4px 15px rgba(102, 126, 234, 0.2); border-left: 4px solid #667eea;">
+                <div style="font-size: 2.5rem;">⚡</div>
+                <div style="font-size: 1.8rem; font-weight: bold; color: #667eea;">{stats.get('elapsed', 0):.2f}s</div>
+                <div style="color: #666; font-size: 0.85rem; margin-top: 0.5rem;">الوقت</div>
+            </div>
+            <div style="background: white; padding: 1.5rem; border-radius: 12px; text-align: center; box-shadow: 0 4px 15px rgba(102, 126, 234, 0.2); border-left: 4px solid #667eea;">
+                <div style="font-size: 2.5rem;">📝</div>
+                <div style="font-size: 1.8rem; font-weight: bold; color: #667eea;">{stats.get('words_count', 0)}</div>
+                <div style="color: #666; font-size: 0.85rem; margin-top: 0.5rem;">كلمة</div>
+            </div>
+            <div style="background: white; padding: 1.5rem; border-radius: 12px; text-align: center; box-shadow: 0 4px 15px rgba(102, 126, 234, 0.2); border-left: 4px solid #667eea;">
+                <div style="font-size: 2.5rem;">📊</div>
+                <div style="font-size: 1.8rem; font-weight: bold; color: #667eea;">{stats.get('chars_count', 0)}</div>
+                <div style="color: #666; font-size: 0.85rem; margin-top: 0.5rem;">حرف</div>
+            </div>
+            <div style="background: white; padding: 1.5rem; border-radius: 12px; text-align: center; box-shadow: 0 4px 15px rgba(102, 126, 234, 0.2); border-left: 4px solid #667eea;">
+                <div style="font-size: 2.5rem;">✨</div>
+                <div style="font-size: 1.8rem; font-weight: bold; color: #667eea;">{stats.get('diacritics_count', 0)}</div>
+                <div style="color: #666; font-size: 0.85rem; margin-top: 0.5rem;">علامة</div>
+            </div>
+            <div style="background: white; padding: 1.5rem; border-radius: 12px; text-align: center; box-shadow: 0 4px 15px rgba(102, 126, 234, 0.2); border-left: 4px solid #667eea;">
+                <div style="font-size: 2.5rem;">🚀</div>
+                <div style="font-size: 1.8rem; font-weight: bold; color: #667eea;">{stats.get('speed', 0)}</div>
+                <div style="color: #666; font-size: 0.85rem; margin-top: 0.5rem;">كلمة/ثا</div>
+            </div>
+            <div style="background: white; padding: 1.5rem; border-radius: 12px; text-align: center; box-shadow: 0 4px 15px rgba(102, 126, 234, 0.2); border-left: 4px solid #667eea;">
+                <div style="font-size: 2.5rem;">🎯</div>
+                <div style="font-size: 1.8rem; font-weight: bold; color: #667eea;">98%+</div>
+                <div style="color: #666; font-size: 0.85rem; margin-top: 0.5rem;">الدقة</div>
+            </div>
+        </div>
+    </div>
+    """
+    
+    output = comparison_html
+    output += f"""
+    <div style="margin-top: 1.5rem; padding: 1.5rem; background: #f8f9fa; border-radius: 12px; font-size: 1.2rem; line-height: 2.2; border-right: 4px solid #28a745; direction: rtl; text-align: right;">
+        {highlighted_result}
+    </div>
+    {stats_html}
+    """
+    
+    return output
+
+with gr.Blocks(
+    title="🎯 مُشَكِّل (الدقيق 98%)",
+    theme=gr.themes.Soft(),
+    css="""
+    body { font-family: 'Arial', sans-serif; }
+    .gradio-container { direction: rtl; }
+    """
+) as demo:
+    
+    gr.Markdown("""
+    # 🚀 مُشَكِّل النصوص (النموذج الدقيق 98%+)
+    <p style='direction: rtl; color: #e74c3c; font-weight: bold;'>
+    ⚠️ تنبيه: هذا النموذج هو الأدق، ولكنه بطيء جداً (20-30 ثانية) لأنه يعمل على سيرفر مجاني.
+    </p>
+    """)
+    
+    clean_text_state = gr.State(None)
+    result_text_state = gr.State(None)
+    stats_state = gr.State({})
+    
+    with gr.Row():
+        with gr.Column(scale=2):
+            input_text = gr.Textbox(
+                label="النص",
+                placeholder="أدخل النص العربي هنا (مشكول أو بدون تشكيل)...",
+                lines=10,
+                max_lines=20
+            )
+            
+            with gr.Row():
+                show_comparison = gr.Checkbox(label="🔄 مقارنة النصين", value=False)
+                highlight_diacritics = gr.Checkbox(label="🎨 تلوين الحركات", value=False)
+            
+            submit_btn = gr.Button("✨ إضافة التشكيل", variant="primary", size="lg")
+    
+    output_html = gr.HTML() 
+    status = gr.Textbox(label="الحالة", interactive=False)
+    
+    gr.Examples(
+        [
+            ["السلام عليكم ورحمة الله وبركاته"],
+            ["اللغة العربية لغة القران الكريم"],
+        ],
+        inputs=input_text,
+        label="أمثلة سريعة"
+    )
+    
+    def show_loading():
+        return LOADING_HTML, "⏳ جاري التشكيل..."
+
+    render_inputs = [
+        clean_text_state, 
+        result_text_state, 
+        stats_state, 
+        show_comparison, 
+        highlight_diacritics
+    ]
+
+    submit_btn.click(
+        fn=show_loading,
+        inputs=None,
+        outputs=[output_html, status]
+    ).then(
+        fn=run_model,
+        inputs=[input_text],
+        outputs=[clean_text_state, result_text_state, stats_state, status]
+    ).then(
+        fn=generate_final_html,
+        inputs=render_inputs,
+        outputs=[output_html]
+    )
+
+    show_comparison.change(
+        fn=generate_final_html,
+        inputs=render_inputs,
+        outputs=[output_html]
+    )
+    
+    highlight_diacritics.change(
+        fn=generate_final_html,
+        inputs=render_inputs,
+        outputs=[output_html]
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+torch
+transformers