tristão on nostr

Open in Damus

#GrapheneOS Speech Services, a high quality on-device text to speech engine built with open source models and training data is now available in the GrapheneOS App Store. https://blossom.primal.net/d...

O Tristão @tristão 1779303388

Is the model ethically sourced. i.e. training data was data you got permission to use?

1

Yes. The data is the public domain LJ Speech dataset. LJ Speech uses user-submitted public domain recordings of audiobooks. LibriVox (audiobook platform) requires all recordings made for them to be in public domain.