Has anyone used a free, offline, open-source, real-time speech-to-speech translation app on under-powered devices (i.e., older smart phones)? There are a few libraries that written that purportedly can do or help with local speech-to-speech:

• https://github.com/ictnlp/StreamSpeech
• https://github.com/k2-fsa/sherpa-onnx
• https://github.com/openai/whisper

I'm looking for a simple app that can listen for English, translate into Korean (and other languages), then perform speech synthesis on the translation. Although real-time would be great, a short delay would work.

RTranslator is awkward (couldn't get it to perform speech-to-speech using a single phone). 3PO sprouts errors like dandelions and requires an online connection.

Any suggestions?

I'm thinking about increasing the level of my open source contributions a bit. Instead of searching blindly until I stumble upon an issue that:
A) Piques my interest
B) I feel somewhat qualified to implement

I figured I'd check with the tildes community. Is there any Open Source software that you use that is missing a feature/capability? Can you give a brief description of it (bonus points for links to an issue tracker with an open ticket :))?

Can't of course promise anything will come of it, but if I do pick up your suggestion at least I'll give you a ping if I make any progress!