It’s all local

Which model would be the best to use for mandarin? Are there any models on par with Parakeet that are just as fast but also understand Chinese?

also is there a way to make parakeet type more naturally? less capitallization, less punctuation? can this be a setting?

this can already be done via local llm processing the text but surely there is an easier way to do this, right

I believe sensevoice, I’ll hopefully be implementing it soon enough