Update README.md

README.md

@@ -1,35 +1,43 @@
-# 🖼️ MuniVis - Multilingual Image Captioning
+# 🛣️ Street Descriptions using MuniVis Model
 
-**MuniVis** is a powerful image captioning application built using the BLIP (Bootstrapped Language-Image Pretraining) model fine-tuned on custom data. It provides image descriptions in both **English** and **Arabic**, making it suitable for multilingual applications, accessibility tools, and urban scene understanding.
+This Space provides a simple Gradio interface for generating image captions using a fine-tuned BLIP model hosted at [`saja003/MuniVis`](https://huggingface.co/saja003/MuniVis). It also includes the option to translate the generated English captions into Arabic using a MarianMT translation model.
 
-## 🔍 What It Does
+---
 
-- Generates English image captions using a fine-tuned BLIP model.
-- Automatically translates captions into Arabic using MarianMT (English → Arabic).
-- Provides a simple web interface powered by [Gradio](https://gradio.app/).
+## 🔍 Features
 
-## 🚀 Demo
+- 🧠 Image captioning with a fine-tuned BLIP model.
+- 🌐 Language selection: English or Arabic.
+- 📸 Upload any street or urban image to generate a descriptive caption.
+- 🤖 Translation powered by [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar).
 
-Try it on [Hugging Face Spaces](https://huggingface.co/spaces/saja003/MuniVis)!
+---
 
-## 📷 How to Use
+## 🚀 How it works
 
 1. Upload an image.
-2. Choose your preferred language (English or Arabic).
-3. The model will analyze the image and generate a meaningful description.
+2. Select a language (English or Arabic).
+3. Receive a descriptive caption of the scene.
+   - If Arabic is selected, the caption is translated automatically.
 
-## 🧠 Model Information
+---
 
-- **Image Captioning Backbone**: `BLIP (Salesforce/blip-image-captioning-base)`
-- **Translation Model**: `Helsinki-NLP/opus-mt-en-ar`
-- **Custom Fine-Tuned Model**: [`saja003/MuniVis`](https://huggingface.co/saja003/MuniVis)
+## 🧠 Models Used
 
-## 📦 Requirements
+- **BLIP (Bootstrapping Language Image Pretraining):**
+  - Fine-tuned on street and infrastructure images.
+  - Model repo: [`saja003/MuniVis`](https://huggingface.co/saja003/MuniVis)
+- **MarianMT Translation Model:**
+  - [`Helsinki-NLP/opus-mt-en-ar`](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) for English to Arabic translation.
 
-This app runs on the following Python packages:
+---
 
-```txt
-torch
+## 🛠️ Requirements
+
+This Space uses the following libraries:
+
+```bash
 transformers
+torch
 gradio
 Pillow