[spdustin]

What about snapping a few frames—maybe 33%, 50% and 66% of the way into the video—and doing a simple face detection?

Perhaps, on top of that, a histogram comparison of the same frames, which should capture if the video is pretty much lyrics on a static background.

[underyx]

1. It's not like all (or even most) music videos have faces in them.

2. I'm pretty sure it's not trivial to download just three specific frames of a video. And downloading so many videos would probably be expensive/bannable.