AI: Machine Learning & Model Training
Training speech models | Sri AI
Advanced
2 views
Course overview
Fine-tune speech recognition on Sri Lankan voices and train text-to-speech voices that sound like people from here.
Level: Advanced · Mode: Part-time
Who this course is for
Engineers building voice products in Sinhala and Tamil.
What you will learn
- Prepare an audio dataset
- Fine-tune Whisper
- Train a text-to-speech voice
- Evaluate with word error rate and listeners
Syllabus
- Module 1: Audio data
- Module 2: Transformer audio models
- Module 3: Fine-tuning speech recognition
- Module 4: Training text-to-speech
- Module 5: Evaluation
Final project
Every module ends in hands-on practice, and the course ends with a project you build and present. Your certificate names that project.
Before you start
Deep learning.
Open-source tools you will use
Adapts the Hugging Face Audio Course (Apache-2.0).