ConwayResearch publishes Underdog Woof, a 40.6 MB English TTS model
The model card claims 1.42% word error rate for Mira and CPU-only synthesis with numpy.
Stories per day · 30 days
2 RSS
Relatedagentic-systems1hugging-face1llm-inference1math-reasoning1open-weights1reasoning-cache1text-to-speech1underdog-woof1
4 stories, newest first · one card per story
Stories tagged #cpu-inference
CPU-ARC caches LLM reasoning traces for cheaper CPU reuse
The paper reports on-par results with frontier models on hard math and science tasks at 16–291x lower cost.
Supersonic Labs Releases Julia 1: A 144.3M-Parameter Open Decision Model That Runs on a CPU
Supersonic Labs released Julia 1, a 144.3M-parameter Apache 2.0 decision model that picks among supplied answers on CPU.
5
Fastino Releases GLiNER2.5-Decide: A 340M Open-Weight Decision Model That Runs on CPU
Fastino Labs released GLiNER2.5-Decide, a 340M Apache 2.0 open-weight decision model for agent routing, triage, and guardrails that runs on CPU.