Lessons from Building a Translator App That Beats Google Translate and DeepL

Re:Lessons from Building a Translator App That Beats Google ... by omneity on Saturday May 03, 2025 @06:38PM (#43882950)

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

[ Parent | on HN ]

Re:Lessons from Building a Translator App That Beats Google ... by klipt on Saturday May 03, 2025 @09:46PM (#43883820)

> 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?

[ Parent | on HN ]