The Data Dilemma 🚀

Open Source AI Solutions • Real-World Impact

✨ About

Building open-source AI tools that solve real-world problems across multiple domains. We specialize in multilingual AI, privacy-preserving solutions, and deployable models with a focus on underserved communities and languages.

🎯 Core Focus: Open Source • Multilingual AI • Privacy-First • Real-World Deployment

🚀 Featured Projects

🎙️ Medibeng-Orpheus TTS

Fine-tuned TTS for Bengali-English code-switching. Built on Orpheus + LLaMA-3b.

🔊 MediBeng Whisper

Lightweight ASR for Bengali-English conversations and translation.

🛡️ MediRag Guard

Privacy-focused RAG system with comprehensive data insights.

💬 GroqStreamChain

Real-time AI chat with FastAPI + WebSocket + Groq.

📄 Research

• Code-switched Translation Models - medRxiv 2025
• Hybrid Deep Learning for Disease Detection - Mathematics 2023
• ML-based Misinformation Detection - Springer 2021

🤝 Contributing

Code: Fork → Branch → PR
Research: Test models, share datasets, collaborate
Community: Documentation, tutorials, discussions

git clone https://github.com/The-Data-Dilemma/[repo-name]
# Make changes, commit, push, PR

🛠️ Tech Stack

AI: HuggingFace • Whisper • Orpheus • PyTorch • Unsloth
Web: FastAPI • WebSocket • Docker
Focus: Multilingual • Code-switching • Privacy • Deployment

📊 Impact

🚀 Open Source Projects: 4+
📝 Research Papers: 3+
🌍 Languages: Bengali + English (expanding)
⭐ Community Stars: 50+

📍 Contact

Email: [email protected]
Location: Khulna, Bangladesh 🇧🇩
LinkedIn: The Data Dilemma