AI: Language & Voice AI
Speech-to-text with open models | Sri AI
Intermediate
3 views
Course overview
Turning speech into text offline, on a server, a laptop or a phone, with Whisper and its faster cousins.
Level: Intermediate · Mode: Evenings, online
Who this course is for
Developers adding voice input to apps, assistants and transcription tools.
What you will learn
- Run Whisper on CPU and GPU
- Transcribe live audio in real time
- Pick the right model size for a device
- Measure accuracy with word error rate
Syllabus
- Module 1: How speech recognition works
- Module 2: Whisper and faster-whisper
- Module 3: whisper.cpp on CPU and phones
- Module 4: Small offline models with Vosk
- Module 5: Streaming and voice activity detection
- Module 6: Measuring accuracy
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
Python for AI.