I have fond memories of cs224d [1] taught by richardsocher. It’s a bit dated at this point as it was created in the pre-transformer era, but it was a very cool introduction to applying deep learning to nlp at the time.

[1] https://cs224d.stanford.edu

Similar thoughts here. That was when I realized the potential of the Internet: I didn't have to be a grad student at a tier 1 research university to learn about the frontier.