I built some AWS infrastructure to batch process audio to automatically generate lyric timings for karaoke, which is useful if you ever want to convert WAP to JSON. 
did you know audacity has a built-in karaoke plugin
i've spent the last few weeks throwing stuff at this machine learning model, and it's hard to stump. it almost always manages to find word boundaries, no matter how unintelligible the lyrics
busta rhymes melting cloud gpus
this technology will allow me to realize my dream of opening a dedicated neil cicierega mashups karaoke bar once the pandemic is over
with bill wurtz songs on thursday nights
