https://github.com/shanebdavis/ai-lang-flashcards
ai-lang-flashcards (ALF) - an experiment in merging AI with flash-cards to maximize language learning the way kids learn
https://github.com/shanebdavis/ai-lang-flashcards
Last synced: 3 months ago
JSON representation
ai-lang-flashcards (ALF) - an experiment in merging AI with flash-cards to maximize language learning the way kids learn
- Host: GitHub
- URL: https://github.com/shanebdavis/ai-lang-flashcards
- Owner: shanebdavis
- Created: 2024-12-30T09:12:48.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-01-11T14:02:07.000Z (5 months ago)
- Last Synced: 2025-01-11T15:19:07.513Z (5 months ago)
- Language: JavaScript
- Size: 2.13 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# AI Language Flashcards (ALF)
Goals
- Learn language through immersion
- Use flashcards to drill in and focus on what you don't know until you know it
- Use AI to make the flashcards interesting and engaging
- Track your progress
# Motivation
I love DuoLingo, but why does every "card" have to be a test? Further, why do I need to switch between Spanish and English every card. I want to learn the same way kids do - by exposure in just one language. I don't want to focus on _translating_ between English and Spanish. I want to focus on _understanding_ the Spanish language. Where a DuoLingo lesion is about 10 cards, I think I can make a compelling flashcard app that helps you study about 100 cards (words) with about the same amount of effort. Further, I have a guess that with AI we might be able to make the flashcards more interesting and engaging.
# Spanish Data
I'm struggling to get good data for Spanish words. What I want is every Spanish word in every conjugation organized by grade level.
Currently I'm working with data from [FrequencyWords](https://github.com/hermitdave/FrequencyWords/tree/master/content/2018/es), but it's kind-of a mess. It contains a lot of English words and proper names. Still, ChatGPT is helping me clean it up.
- [words-all.csv](src/data/words-all.csv)
- Processed with ChatGPT: [convert-openai.js](src/data/convert-openai.js)
- [github/SpanishDictionaryCreator](https://github.com/nhershy/SpanishDictionaryCreator)