π― What is this tutorial for?
This tutorial provides a complete, hands-on workflow for aligning speech recordings at the phone level using WhisperX and the Montreal Forced Aligner (MFA). It is designed for linguists, speech researchers, and language students, especially those without a technical background who want to benefit from large AI models without writing complex code.
The instructions are based on real deployment experience and include platform-specific notes, common pitfalls, and practical scripts for batch processing.
π Download the Full Tutorial
From Audio to Phone-Level Alignment Using WhisperX and MFA_20June.pdf
π Download the Python Script
β Optional: How to Cite
If this tutorial or script saves you time or helps in your project, a mention or citation would be greatly appreciated!
Jingyi Sun (2025). From Audio to Phone-Level Alignment Using WhisperX and MFA. Available at: https://www.notion.so/From-Audio-to-Phone-Level-Alignment-Using-WhisperX-and-MFA-218d6663b67a807d9d07f6549172141f
Written by Jingyi Sun,
Laboratoire de PhonΓ©tique et Phonologie (CNRS & Sorbonne Nouvelle), Paris, June 2025.