Update README.md

README.md

@@ -1,98 +1,12 @@
-Absolutely! Here’s the full rephrased content you can easily copy and paste:
-
-⸻
-
-
-
-# Image Description and Audio Transcript App
-
-An AI-powered web app that identifies objects in images and converts the generated descriptions into speech using Hugging Face Transformers.
-
----
-
-## Overview
-This project showcases how to build a pipeline using:
-- **BLIP** for image captioning  
-- **gTTS** (Google Text-to-Speech) for audio generation  
-- **Gradio** for the user interface and deployment on Hugging Face Spaces
-
----
-
-## What It Does
-- Upload an image → Get an AI-generated description  
-- Automatically convert the description into audio  
-- Built with accessibility in mind for users with visual impairments  
-- Runs on a clean, responsive web UI using **Gradio**
-
----
-
-## Tech Stack
-- **Language**: Python 3.7+
-- **AI Models**:
-  - `Salesforce/blip-image-captioning-base` – for generating image captions
-  - `gtts` – for converting text into speech
-- **Frameworks/Libraries**:
-  - `torch` – powering the models
-  - `transformers` – loading and running pre-trained models
-  - `gradio` – creating the interactive frontend
-  - `Pillow`, `matplotlib`, `inflect` – for image handling and fine-tuning the output
-
 ---
-
-## Installation
-
-1. **Clone the repo** (or upload files to your Hugging Face Space):
-```bash
-git clone https://github.com/your-username/image-caption-audio-app.git
-cd image-caption-audio-app
-
-	2.	(Optional) Create a virtual environment:
-
-python -m venv venv
-source venv/bin/activate  # For Windows: venv\Scripts\activate
-
-	3.	Install dependencies:
-
-pip install torch transformers gtts gradio Pillow matplotlib inflect
-
-If you’re using Hugging Face Spaces, simply include a requirements.txt file with those packages.
-
-⸻
-
-How to Run
-
-Locally:
-
-python object_detection.py
-
-Then visit: http://127.0.0.1:7860 in your browser.
-
-On Hugging Face:
-Just upload all files (including requirements.txt) to your Space. It’ll launch automatically.
-
-⸻
-
-Customizations
-
-You can tweak parameters (like host, port, or debug settings) directly in the script if needed. For example:
-
-gr.Interface(...).launch(server_name="0.0.0.0", server_port=7860, debug=True)
-
-
-
-⸻
-
-Credits
-	•	Hugging Face for the BLIP model
-	•	Google for gTTS
-	•	Gradio for simplifying deployment and UI creation
-
-⸻
-
-License
-
-MIT License – Feel free to use, share, and modify.
-
+title: Object Detection App
+emoji: 🧠
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+sdk_version: "4.20.0"
+app_file: app.py
+pinned: false
 ---
 
-Let me know if you'd like a version with your name, GitHub link, or any branding!
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference