Open Source Models with Hugging Face

📚 About the Course

This repository contains my personal practice projects and notes based on the Open Source Models with Hugging Face course powered by DeepLearning.AI and Hugging Face.
All modules have been practiced, implemented, and extended by myself as part of hands-on learning.

🚀 Topics Covered

• Introduction to Open-Source Models
• Hugging Face Hub: Uploading and Sharing Models
• Fine-Tuning Pretrained Models
• Creating Model Cards
• Best Practices for Open-Source Contributions
• Natural Language Processing (NLP)
• Translation and Summarization
• Sentence Embeddings
• Zero-Shot Audio Classification
• Automatic Speech Recognition
• Text to Speech
• Object Detection
• Image Segmentation
• Image Retrieval
• Image Captioning
• Multimodal Visual Question Answering
• Zero-Shot Image Classification
• Deployment to Hugging Face Hub

🛠 Tech Stack

• Python
• Hugging Face Transformers
• Hugging Face Datasets
• Hugging Face Hub
• Sentence-Transformers
• Google Colab / Jupyter Notebook
• Gradio
• PyTorch
• Torchvision

📂 Repository Structure

├── NLP_Module.py
├── Sentence_Embeddings.py
├── Translation_Summarization.py
├── Zero-Shot_Audio_Classification.py
├── Automatic_Speech_Recognition.py
├── Text_to_Speech.py
├── Object_Detection.py
├── Segmentation.py
├── Image_Retrieval.py
├── Image_Captioning.py
├── Multimodal_Visual_Question_&_Answering.py
├── Zero-Shot_Image_Classification.py
├── Deployment.py
└── README.md

📉 Modules Overview

NLP Module

• A simple chatbot interface using BlenderBot and Hugging Face pipelines.

Translation and Summarization Module

• Translate English text to French and summarize long documents using pretrained models.

Sentence Embeddings Module

• Generate and compare sentence embeddings using MiniLM model.

Zero-Shot Audio Classification Module

• Classify audio clips without training using CLAP model.

Automatic Speech Recognition Module

• Transcribe speech audio to text using Distil-Whisper.

Text to Speech Module

• Convert input text into synthesized speech.

Object Detection Module

• Detect objects in images using a DETR model and visualize with Gradio.

Image Segmentation Module

• Perform semantic segmentation and generate masks with SAM model.

Image Retrieval Module

• Retrieve similar images using embedding search.

Image Captioning Module

• Generate captions for images using BLIP model.

Multimodal Visual Question Answering Module

• Answer questions based on image input with BLIP-VQA.

Zero-Shot Image Classification Module

• Classify images into custom categories using CLIP model.

Deployment Module

• Deploy fine-tuned or custom models to the Hugging Face Hub.

🧐 Skills Learned

• Fine-tuning Transformers on custom datasets
• Publishing models to Hugging Face Hub
• Managing model versions
• Natural Language Processing
• Machine Translation
• Text Summarization
• Sentence Similarity
• Audio and Speech Processing
• Image Retrieval
• Image Captioning
• Visual Question Answering
• Object Detection and Segmentation
• Zero-Shot Learning
• Model Deployment

📌 How to Use

Clone the repository:

git clone https://github.com/your-username/open-source-models-huggingface.git
cd open-source-models-huggingface

Run the modules:

python NLP_Module.py
python Translation_Summarization.py
python Sentence_Embeddings.py
python Zero-Shot_Audio_Classification.py
python Automatic_Speech_Recognition.py
python Text_to_Speech.py
python Object_Detection.py
python Segmentation.py
python Image_Retrieval.py
python Image_Captioning.py
python Multimodal_Visual_Question_&_Answering.py
python Zero-Shot_Image_Classification.py
python Deployment.py

✨ Author

• Nooruddin – GitHub | 📧 [noor.cs2@yahoo.com]