* Basic scrolling emoji menu, with latest emoji and skin tones
* Theming using preset themes and dynamic colors
* Integrated voice input (using whisper.cpp and faster models)
* Swipe the spacebar to move cursor, swipe the delete key to delete
* System personal dictionary gets prompted to transformer model and voice input
Current limitations:
* Languages other than English are not well supported
* Model finetuning is implemented and enablable, but needs more evaluations and tuning
* Emoji menu is very limited
# Roadmap
Short-term:
* Improve model to suggest emojis and more texting-style text
* Improve emoji menu
* Togglable blacklisting of offensive/vulgar words
* Ability to long-press to remove words from being suggested
* Improve the built-in dictionary by removing some entries that are potentially annoying (common misspellings of common words that the dictionary contains as a capitalized acronym, e.g. jts becomes JTS instead of it's)
* Stability improvements, bug fixes, quality of life improvements
Short to mid term:
* Improved onboarding, explaining the various features
* Support other languages for the built-in voice input
* Automatic personal dictionary, take common user words and feed them to models automatically so that the user doesn't have to manually add them
* Algorithm improvements, better dealing with plurals, etc
Mid-term:
* The actions need to be customizable, draggable, removable, instead of being hardcoded into their places
* Improved modularity, possibly allow importing keyboard layouts, dictionaries and models all as one file
* Improve model fine-tuning, evaluate to figure out the best method of training
