Can you train a state of the art text-to-speech (TTS) model with little resources? It seems you can! I've used Google's free TPU research credit to train a Dutch version of "Dia" called Parkiet, a natural conversation speech model and the quality is on-par with ElevenLabs.

Finished the Duolingo-like daily exercises for news content. You can try it out at app.fluentsubs.com/exercises/da... for 11 languages (will add more soon). Tomorrow I'll finally do some proper marketing and fix the membership option (basically everything is free) #buildinpublic #langsky

DuoLingo like exercises for YouTube content is coming to Fluentsubs! #buildinpublic #langsky

In a major upgrade to Fluentsubs I've added "cloze" for subtitles. Based on the accuracy of the transcript and the word length, random gaps are created as a listening exercise to the user to bridge the gap between reading/listening skills in a language. #buildinpublic #langsky

Fluentsubs just got smarter! 🚀 Now you can pick only the part that you need for your deck—perfect for short spaced repetition cards. Check it out! 📚✨ #LanguageLearning #buildinpublic

Had some nice feedback from the first users and implemented the playlist feature, and added some basic channels so beginner language learners are not completely overwhelmed. The videos are pre-transcribed so that they can be watched immediately! #langsky #japanese #buildinpublic

Finished a complete overhaul of the spaced repetition implementation for my language learning app. Text input and hints are now available when rehearsing flashcards.

Still buggy on mobile 🤞 #buildinpublic

Streak and XP learning system is almost implemented. #buildinpublic

It is now possible in Fluentsubs to automatically add words from your own video content to your collections based on your language learning level! #buildinpublic #langsky