alt Hacker NewsDo you have any accuracy benchmarks?
I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.
Although for the use cases OP is targeting, lower accuracy may be good enough!
Replies
kamranjon • yesterday at 10:07 PM
If you look at this chart here it seems the tiny model has a WER of ~12%… not sure about the micro model:
https://github.com/moonshine-ai/moonshine#when-should-you-ch...
➕ show 1 reply
> I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.
This actually holds for everything in AI.