Thanks for the tip and cool project! The model I trained is relatively large, as it's a single model that supports all language pairs (to leverage transfer learning).

With that said while running it client-side is indeed an option, openly distributing the model is not something I would like to do, at least at this stage. Unlike the bigger projects in the NMT space, including Marian and Bergamot, I don't have any funding, and my monetization plan is to offer inference via API[0].

0: https://api.sawalni.com/docs

> I trained is relatively large, as it's a single model that supports all language pairs (to leverage transfer learning).

Note that you have the larger model, if you wanted a smaller model for just one language pair, I guess you could use distillation?