jkoff
Most of the testing so far is English/French/Japanese/Mandarin, but I'm eager to add more languages if anyone is fluent and willing to help me evaluate the text-to-speech.
I'm working on a web app that creates easy-to-understand stories and explainers for the sake of language learning. You can listen in your favourite podcast app, or directly on the website with illustrations.
I'm eager to add more languages if anyone is fluent/able to help me evaluate the text-to-speech.
I'm working on a web app that creates easy-to-understand stories and explainers for the sake of language learning. You can listen in your favourite podcast app, or directly on the website with illustrations.
I've mostly focused on Japanese and French, but I'm eager to add more languages if anyone is able to help me evaluate the text-to-speech for that language.
I'm building Infinite Pod, a web app that generates language learning podcasts tuned to your individual learning goals and level.
It's based on the principle of language acquisition through comprehensible input, as described here: https://www.youtube.com/watch?v=NiTsduRreug
It's still a bit rough, but feels magical in my own testing so I wanted to make it available to others.
It's not available publicly yet, but works well for my purposes and I'm working on productionizing it. Sign-up page for updates: https://letmeknow.jkoff.ca/infinite-ci
As far as where I'm at: - I've listened to it in my target language for N hours. To my ear, it sounds correct and I've learned some new words that I then heard used consistently in native media. - Next, I'd like to set it to teach me a language that I already know, so that I can more reliably and easily spot errors. This will require some changes, since my target language is currently hardcoded. - Longer-term, validation based on languages I speak can't generalize 100% to other languages, nor can validation of version N make assertions about version N + 1. Correctness would benefit from native speakers periodically checking results, and usefulness would benefit from user feedback (even if only in the form of engagement or lack thereof).
Try it here: http://uberpro.nko2.nodeknockout.com/
Info page: http://nodeknockout.com/teams/4e24c9fe4d4c760100001495