Do you happen to know why Orpheus and Llasa use Finetuning for voice cloning? Zo... | Hacker News

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

		oezi 11 months ago \| parent \| context \| favorite \| on: Llasa: Llama-Based Speech Synthesis Do you happen to know why Orpheus and Llasa use Finetuning for voice cloning? Zonos uses 128-float embeddings for voices and it seems so much nicer. Because you can just mix and match voices without changing the model.

thot_experiment 11 months ago [–]

No, you just condition it with text-voice token pairs and then when conditioning further inference w/ text the voice tokens tend to match the pairs further up in the context.

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