Earlybird: a 29M-parameter predictive speech-to-text model that outputs words 90ms before you finish saying them
DrDatta_AIIMS · x · 2026-11-12
Developer sahilmdkr released Earlybird, a tiny 29M-parameter predictive speech-to-text model that outputs words before you finish saying them.
- Most streaming ASR models wait 90-400ms after a word ends before emitting it; Earlybird correctly predicts words a median of 90 ms before they end.
- That predictive output slashes perceived latency, useful for live captions and voice agents.
The model and code are open-sourced on GitHub.
More from Research
- Axiom Math formalization finds broken step in finite simple group classification proof — jiqizhixin · 2026-11-12
- SimEX: agents learn manipulation skills in imperfect simulation and transfer them to real robots — chris_j_paxton · 2026-11-12
- Lie bracket visualized: how second-order residue lets wheeled robots move without sliding — burny_tech · 2026-11-12
- On PostTrainBench, AI post-training now beats the human-tuned SmolLM3-3B from the same base — maksym_andr · 2026-11-12
- FigBrains: models are outpacing our ability to build training environments by hand — vsikka · 2026-11-12
- Open CHI Reviews site archives real CHI peer reviews, crowdsourced from authors — IanArawjo · 2026-11-12