Real-time speech-to-speech translation

The combination of things you are asking for is a challenge. Certainly combining offline use with underpowered devices. Specifically, the under-powered device bit is making it a next to impossible ask, I think. As for accurate speech to text and accurate translation you do likely need to run two models, a good speech to text model supporting both languages. A LLM also trained reasonably well in both languages, ideally trained to do translation. There are other options, but the result there likely will be much more crude.

As far as RTranslator goes, I was doing a quick google search myself and came across their repo. The online remark makes me think you used the v1.0 version of it, the v2.0 version does everything on your phone. According to their github anyway, but they also make it clear there are minimum hardware requirements for it to have any reasonable chance of working:

I have optimized the AI models a lot to minimize RAM consumption and execution time, despite this however to be able to use the app without the risk of crashing you need a phone with at least 6GB of RAM, and to have a good enough execution time you need a phone with a fast enough CPU.

Edit:

I might not be entirely right, I also came across LibreTranslate which for translation uses a offline library called argos-translate which still uses neural machine translation but might have slightly lower hardware requirements? Not entirely sure about that last bit, but figured I'd throw it in there.

This almost certainly not what you're looking for, but the translation app on Apple Watch has passable translation and can work offline with a number of commonly-spoken language. I just tested it with English and Japanese and my pre-K understanding of the language was perfectly satisfied with it. The app works much the same on iPhone as well, but with more features.

The thing that you'll have a hard time with is the "real time" part. You'll likely never have a translation software that can talk back at the same speed you'd see, for instance, a dub on top of a speaker in a finished video. At least when it comes to languages with differing sentence structure. In those cases, you generally need to have the entire idea of the sentence to come through before it can reliably start translating.