MacOS ARM chip won't compile libtorch for transformer library

I'm having trouble getting this library GitHub - guillaume-be/rust-bert: Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...) to run.

See the issue here -

In essence, the MacOS ARM chip uses pytorch/libtorch in such a way that the library won't compile. There have been several proposed solutions but none of them seem to work. I'd like to use this library, but it doesn't look like it will work.

Does anyone have any ideas?