Update app.py

app.py

@@ -14,36 +14,80 @@ model_en = BlipForConditionalGeneration.from_pretrained(model_path)
 model_en.eval()
 
 # Function to describe image
+@torch.no_grad()
 def describe_image(image, language):
-    if language == "Arabic":
-        inputs = processor_en(image, return_tensors="pt")
-        with torch.no_grad():
-            out = model_en.generate(**inputs)
-        description = processor_en.decode(out[0], skip_special_tokens=True)
-        inputs_ar = translator_tokenizer_ar(description, return_tensors="pt")
-        with torch.no_grad():
-            translated_tokens = translator_model_ar.generate(**inputs_ar)
-        arabic_description = translator_tokenizer_ar.decode(translated_tokens[0], skip_special_tokens=True)
-        return arabic_description
-
-    elif language == "English":
-        inputs_en = processor_en(image, return_tensors="pt")
-        with torch.no_grad():
-            out_en = model_en.generate(**inputs_en)
-        description_en = processor_en.decode(out_en[0], skip_special_tokens=True)
-        return description_en
+    pil = image if isinstance(image, Image.Image) else Image.fromarray(image)
+
+    # وصف بالإنجليزية
+    inputs = processor_en(pil, return_tensors="pt")
+    out_ids = model_en.generate(**inputs)
+    en_desc = processor_en.decode(out_ids[0], skip_special_tokens=True)
+
+    # الترجمة إذا اللغة عربية
+    if str(language).lower().startswith(("ar", "arabic")) or language == "العربية":
+        inputs_ar = translator_tokenizer_ar(en_desc, return_tensors="pt")
+        ar_tokens = translator_model_ar.generate(**inputs_ar)
+        ar_desc = translator_tokenizer_ar.decode(ar_tokens[0], skip_special_tokens=True)
+        return ar_desc
+    else:
+        return en_desc
+
+ASIR_BBOX = {
+    "lat_min": 17.0,  "lat_max": 20.0,
+    "lon_min": 41.5,  "lon_max": 44.0,
+}
+
+def random_point_in_bbox(bbox):
+    lat = random.uniform(bbox["lat_min"], bbox["lat_max"])
+    lon = random.uniform(bbox["lon_min"], bbox["lon_max"])
+    return round(lat, 6), round(lon, 6)
+
+def render_html(caption_text, lat, lon, language="English"):
+    now = datetime.datetime.now()
+    dt_str = now.strftime("%d %B %Y - %I:%M %p")
+
+    is_ar = str(language).lower().startswith(("ar", "arabic")) or language == "العربية"
+    dt_line  = f"🕒 {'التاريخ والوقت' if is_ar else 'Date & Time'}: {dt_str}"
+    loc_label = "📍 الموقع" if is_ar else "📍 Location"
+
+    zoom = 16
+    osm_iframe = (
+        f'<iframe width="100%" height="300" frameborder="0" '
+        f'src="https://www.openstreetmap.org/export/embed.html?layer=mapnik&marker={lat}%2C{lon}&zoom={zoom}"></iframe>'
+        f'<div style="font-size:12px;color:#aaa;margin-top:4px">{loc_label}: {lat}, {lon} '
+        f'• <a target="_blank" href="https://www.openstreetmap.org/?mlat={lat}&mlon={lon}#map={zoom}/{lat}/{lon}">Open map</a>'
+        f'</div>'
+    )
+
+    return f"""
+    <div style="font-family:system-ui,Segoe UI,Arial;color:#eee;line-height:1.5">
+      <div style="background:#1f1f1f;padding:14px 16px;border-radius:10px;margin-bottom:10px;">
+        <div style="font-size:16px;white-space:pre-wrap;">{caption_text}</div>
+      </div>
+      {osm_iframe}
+      <div style="margin-top:8px;font-size:14px;">{dt_line}</div>
+    </div>
+    """
+
+def ui_print_like(image, language):
+    caption = describe_image(image, language)
+    lat, lon = random_point_in_bbox(ASIR_BBOX)
+    return render_html(caption, lat, lon, language)
+
+
 
 # Gradio UI
-iface = gr.Interface(
-    fn=describe_image,
+demo = gr.Interface(
+    fn=ui_print_like,
     inputs=[
-        gr.Image(type="pil", label="Upload an Image"),
-        gr.Dropdown(choices=["Arabic", "English"], label="Select Language")
+        gr.Image(type="pil", label="Upload road image"),
+        gr.Dropdown(choices=["Arabic", "English", "العربية"], value="English", label="Select Language")
     ],
-    outputs="text",
-    title="Image Captioning with Arabic Translation",
-    description="Select the language and upload an image to get a description."
+    outputs=gr.HTML(label="output"),
+    title="MuniVis – Road Issue Detector (Asir)",
+    description="Upload an image and get a description with a map (Asir random location) and date/time."
 )
 
-if __name__ == "__main__":
-    iface.launch()
+demo.launch(debug=True)
+
+