Learning Chinese and Japanese with graphs and trees
Just for fun, I built a language learning tool. It represents Chinese and Japanese as graphs of characters, with connections indicating given characters can form a word. It can also decompose characters to give clues on how they're pronounced, analyzes words to understand which ones are commonly used together, and more. It's fully interactive, supports offline use, generates flashcards, has sentences from humans and from AI, and plenty of other features. Check out the README for details. https://github.com/mreichhoff/HanziGraph
Does the same job
all alternatives →- AAAn “automatic” way to learn Chinese2018 · play.google.com · ▲57
- NSNihongo – Study Japanese using authentic text from games, songs, etc.2015 · nihongo-app.com · ▲139
- AFApp for learning how to write Japanese2012 · ▲55
I'm a long time lurker that recently quit my job to work on my own projects, a lot due to the inspiration from Hacker News. Now I have published my first serious project, an app for learning how to write Japanese characters. It's the app I always wanted but couldn't find when I was studying. It tries to be simple to use, you just start the quiz and go with the flow. There's no need to plan and manage your studies, and it uses spaced repetition for better retention. There's a promo page with more details up at http://www.kanjibyhand.com. It's only for Android so far. The free version includes…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, February 2024
the whole month →
MarketingIdeas.com▲1,230Never run out of marketing ideas ever again
Growth · 2024 · marketingideas.com
