Signals 4 · free daily AI digest

Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model

Paper recorded by Signals 4 on 2026-10-05 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-05 on arXiv · recorded by Signals 4 on 2026-10-06

Category: cs.AI · 人工智能 · first seen 2026-10-06

Abstract

We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher. It has 10x fewer parameters and needs 15x less compute. We first synthesize a corpus with the teacher and keep its du

Read on arXiv →

#451 most recent of 980 cs.AI papers we have recorded · ↑ newer: Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Tow · ↓ older: TAPDreamer: Transferable Adversarial Patches for World Action Models

Cite this page: Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model: the #451 most recent of 980 cs.AI papers we have recorded (as of 2026-10-05). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/paradee-distilling-kokoro-82m-into-an-8m-parameter-single-voice-text-to-speech-m.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json

Related: More cs.AI papers · arXiv signals · All papers · Today in AI

Get 4 AI signals a day by email — free.

Subscribe free → See all plans →

Get 4 AI signals a day by email — free

All models · All repos · By company · Daily editions