Damus
GrapheneOS profile picture
GrapheneOS
@GrapheneOS
We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data. It will be added to our App Store soon and then included in GrapheneOS as a default enabled TTS backend once some more improvements are made to it.
611❀️12❀️3πŸ”₯3❀1πŸŽ‰1πŸ‘€1
Phillip Plays · 33w
nostr:nprofile1qy2hwumn8ghj7un9d3shjtnyd968gmewwp6kyqpqtva8g98fx0fks0pt38vr75tv02t30qd5ev7n5v7fcpl6t44hf7kqzp8d0p very very cool!
GrapheneOS · 33w
We're going to build our own speech-to-text implementation to go along with this too. We're starting with an English model for both but we can add other languages which have high quality training data available. English and Mandarin have by far the most training data available.
Breizh · 33w
nostr:nprofile1qy2hwumn8ghj7un9d3shjtnyd968gmewwp6kyqpqtva8g98fx0fks0pt38vr75tv02t30qd5ev7n5v7fcpl6t44hf7kqzp8d0p Well, some times ago, open-source TTS was pretty lacking, but now Kaldi / Sherpa is pretty good, did you check it? If yes, what was the problem with it?
Dan · 33w
More movement to full function with less intrusion. Nice!
Marcial πŸ‡¨πŸ‡·πŸ‡»πŸ‡ͺ · 33w
nostr:nprofile1qy2hwumn8ghj7un9d3shjtnyd968gmewwp6kyqpqtva8g98fx0fks0pt38vr75tv02t30qd5ev7n5v7fcpl6t44hf7kqzp8d0p For those who do not have neither GitHub accounts or crypto, do y’all have plans to set up funding channels through the likes of LiberaPay, OpenCollective, etc?
Ethin Probst · 33w
nostr:nprofile1qy2hwumn8ghj7un9d3shjtnyd968gmewwp6kyqpqtva8g98fx0fks0pt38vr75tv02t30qd5ev7n5v7fcpl6t44hf7kqzp8d0p Does this follow the Android TTS API? Or does it have it's own?