facebookresearch/brain2qwerty

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.

Python

1,130

3 commits

updated Sep 24, 2026

See the code

README

Brain2Qwerty

Decoding Sentences from Non-Invasive Recordings of the Brain.

A participant types in an MEG scanner; Brain2Qwerty reconstructs the sentence from brain activity.

Documentation

Publications

Non-invasive decoding of typed sentences from human brain activity (Nature Neuroscience, 2026).
Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings (preprint, 2026).

Code

Infrastructure

License

The code is released under CC BY-NC 4.0.

Data

Brain2Qwerty v1: https://huggingface.co/datasets/bcbl190626/SpanishBCBL
Brain2Qwerty v2: under embargo until the paper acceptation.

The datasets are collected by and belong to the BCBL — Basque Center on Cognition, Brain and Language.

Significant stargazers

rUv

11,749 followers · starred Jun 2026

Rupesh Sreeraman

247 followers · starred Jun 2026

samy kamkar

11,920 followers · starred Jul 2026

Christopher Akiki

133 followers · starred Jun 2026

Similar repos

facebookresearch/tribev2

This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain…

3,294

same org

bcbl190626/SpanishBCBL

Dataset

DECOMEG — Brain Activity During Typing (MEG & EEG)

LidongYang/BrainFLORA

Dataset

BrainFLORA Dataset and Checkpoints

willxxy/awesome-mmps

Corpus of resources for multimodal machine learning with physiological signals (mmps).

167

athms/learning-from-brains

Self-supervised learning techniques for neuroimaging data inspired by prominent learning frameworks…

110

microsoft/automated-brain-explanations

Generating and validating natural-language explanations for the brain.

wenhuic/Neuro-GPT

Model

Neuro-GPT: Towards a Foundation Model for EEG paper

ncclab-sustech/BrainFLORA