Moi!
Any thoughts/ideas on how this can be hooked up with whisper and either a poro or viking model to get a fullstack speech-to-text-to-speech for practicing and learning Finnish? Is text2wave the best model for this locally? I know elevenlabs has great models, but they aren't cheap! Could facebooks MMS models do better you think?
Moi!
Any thoughts/ideas on how this can be hooked up with whisper and either a poro or viking model to get a fullstack speech-to-text-to-speech for practicing and learning Finnish? Is text2wave the best model for this locally? I know elevenlabs has great models, but they aren't cheap! Could facebooks MMS models do better you think?