architecture · first seen 10 Nov 2026
diffusion head for continuous audio latents
Generating continuous speech latents with a diffusion head on top of a language-model backbone.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Alania-2: Turkish text-to-speech with instant and fine-tuned voice cloningPapers · 10 Nov 2026 · Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas
Latest sources
- Alania-2: Turkish text-to-speech with instant and fine-tuned voice cloningPapers · 10 Nov 2026 · Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas