Kursai-loip/samburu-tts

# Samburu TTS Project # Samburu TTS – Roadmap and Colab Notebooks Improving the Facebook MMS-TTS model for Samburu language pronunciation accuracy. --- ## 🚀 Quick Start Each notebook below opens directly in **Google Colab** (GPU runtime recommended). | Notebook | Colab Link | |-----------|-------------| | 01 – Inspect Baseline | | | 02 – Phoneme Cleanup | | | 03 – Dataset Preparation | | | 04 – LoRA Fine-tuning | | | 05 – Vocoder Tuning | | | 06 – Inference & Deployment | | --- ### 💡 How to Use 1. Click a badge above to open the notebook in Colab. 2. Go to **Runtime → Change runtime type → GPU**. 3. Run cells step-by-step as guided in the comments. 4. Save and commit any working version back to GitHub. --- ### 📘 Notes - Base model: `facebook/mms-tts-saq` - Fine-tuning goal: Improve pronunciation accuracy and audio clarity for Samburu. - All notebooks are modular — progress from 01 → 06 in order. --- *Maintained by Kursai-loip*