---
title: Street Descriptions using MuniVis
emoji: 🛣️
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 5.26.0
app_file: app.py
pinned: false
---

# 🛣️ Street Descriptions using MuniVis Model

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.

---

## 🔍 Features

- 🧠 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).

---

## 🚀 How it works

1. Upload an image.
2. Select a language (English or Arabic).
3. Receive a descriptive caption of the scene.
   - If Arabic is selected, the caption is translated automatically.

---

## 🧠 Models Used

- **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.

---

## 🛠️ Requirements

This Space uses the following libraries:

```bash
transformers
torch
gradio
Pillow