VUI – open-source Jarvis stack with a 300M TTS Model 2 months ago
What's the buisness?
HN user
What's the buisness?
thanks!
Haha yeah this is the idea
Definitely possible but tricky with stacks > 1B in params
Sad to not see vui on the comparisons!
A 100M podcast model
fluxions.ai has a similar model
As someone who has worked in TTS for over 4 years now. I can tell you that evaluation is the most difficult aspect of generative audio ML.
How will this really check that the models are performing well vs just listening?
Let it die