TynanSigg
Edit: I thought the model in the above paper was pre-trained, but apparently it's only trained on the data as it arrives! That's indeed a very interesting approach, I wouldn't have expected that neural network models would converge quickly enough for it to be useful.
Here's the code if anyone's interested: https://github.com/trsigg/lm-compression . I haven't looked at it in a while except for updating it today to work with more recent versions of the transformers library, but I think it should still function and is pretty easy to try out with different models. I thought about using something like a hidden Markov model instead which would be much faster (even more so because it would enable using tabled rather than range-based ANS), but I haven't gotten around to it.