Brain2Qwerty
Typing decoded from non-invasive brain recordings
Latest: Brain2Qwerty v2 — trained on 10x more data per participant, up to 78% word accuracy for the best participant
A non-invasive brain-to-text system from FAIR and the Basque Center on Cognition, Brain and Language (February 2025): as participants type sentences, a convolution-transformer-language-model stack decodes the text from MEG or EEG alone. MEG reached a 32% character error rate on average — 19% for the best participant — without surgery.
Why it matters
Non-invasive brain-to-text without surgery: decoding typed sentences from MEG reached a 32% character error rate (19% for the best participant) in v1, and v2 lifted the best participant to 78% word accuracy, with accuracy scaling log-linearly with data. Published in Nature Neuroscience with code open.
Facts
- The open repo has ~900+ GitHub stars; v2 decodes full sentences from continuous MEG in a streaming fashion — an early glimpse of typing-free communication for people who cannot speak or move.
Try it yourself
Project page with results explorer ↗ Code on GitHub ↗ Read the Nature Neuroscience paper ↗
Lineage
Sources
arXiv ↗Meta AI research ↗facebookresearch.github.io ↗