Kyutai Retrains PocketTTS With Simpler Loss, Hitting 0.90% Word Error Rate

Kyutai trained its 100M-parameter on-device text-to-speech model with a new one-step generative objective, hitting sub-1% WER without Jacobian-vector products.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-10-01 15:17 · AlphaSignal
Kyutai Retrains PocketTTS With Simpler Loss, Hitting 0.90% Word Error Rate

More stories

Bring near-Astra intelligence to everyday work with GPT-6.1 Sol on Amazon Bedrock — AWS Machine Learning Blog
Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs — Allen Institute for AI (Ai2)
OpenAI DevDay 2026 Keynote (FULL) — OpenAI YouTube
Introducing dots — OpenAI News
Introducing Claude Sonnet 5.5 on AWS — AWS Machine Learning Blog
OpenAI Says It Will Not Release Newest Astra A.I. Model Over Safety Concerns — New York Times Technology
Google's first Gemini 4 model is 'Argon' — Engadget
Ollama now supports Jev-style decision models — Ollama Blog

Get the daily brief of stories like this at 6:30 every morning →