- On-device translation using Mozilla’s translation models
- Transliteration of non-latin script
- OCR (Optical Character Recognition) for translating text in images
- Automatic language detection
- Image translation overlay that preserves original formatting
- Support for multiple language pairs
- No internet required for translation once models are downloaded
- All translation happens locally
Cool this is nice! Just confirming, the image translation is only for OCR, right? I mean it doesn’t translate a photo of a menu in a restaurant or am I missing something?
yooo this looks dope. Thanks for sharing
Indeed. Commenting to install later at home.
Awesome recommendation, thanks!
Been using it for a while and it works quite well for what it is. It also overlays the translated text on the original image which is nice. The translation engine is the exact same one as the one in firefox and its forks, so dont expect deepl levels but its still perfectly fine for most casual use cases.
my only gripe with it is it should be able to be used as a system assistant ala google lens so i can just hold down circle and activate it
Yeah, I use it as well and the level of translation is simmilar to the level of google translate in the early 2010s. The main problem it has is that the OCR is not great. It can only detect very clear horizontal texts and has problems in any other use case. Also it gives you a translation but no alternatives that might be good depending on the context but I think that might be outside the scope of this model.
i use it quite a lot. very useful also in-line translation: you select some text and the context menu offers translation directly without opening the full app.
I’m wondering how ff models compare to smth more modern, like the recent translateGemma stuff (given 12b models reportedly run fine on phones nowadays)
