I don't know what I'm talking about, but could you use distillation techniques? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		nardi 8 months ago \| parent \| context \| favorite \| on: Show HN: Real-time AI Voice Chat at ~500ms Latency I don't know what I'm talking about, but could you use distillation techniques?

koljab 7 months ago [–]

Maybe possible, I did not look into that much for Coqui XTTS. What i know is that the quantized versions for Orpheus sound noticably worse. I feel audio models are quite sensitive to quantization.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact