≡
#huggingface
2024.11.16 Forced Alignment using HuggingFace Wav2Vec2 Models: Part 2 In this second part of my weekend project, I use a dynamic programming algorithm to align audio and lyrics. 2024.11.10 Forced Alignment using HuggingFace Wav2Vec2 Models: Part 1 In this first part of my weekend project, I isolate audio and get a transcript using machine learning.