Fine-tuning Zyphra's ZUNA1.1 EEG foundation model on the Temple University Hospital EEG Corpus — the largest public clinical EEG dataset. AGPL-3.0 code, CC-BY-4.0 data. No closed-source profiteering from this research.
Clinical EEG is underserved by AI. Most existing models are proprietary, gated behind vendor licenses, or trained only on healthy subjects rather than real clinical seizure and non-seizure recordings. ZUNA1.1 is a 380M-parameter diffusion autoencoder that can reconstruct, denoise, and upsample EEG from any montage — but it was trained on public research datasets, not clinical-grade data. This project fine-tunes it on real hospital recordings and publishes the result freely, so researchers and clinics don't have to buy access to a black box.
ZUNA1.1 "thought-to-text" demo — the base model this project fine-tunes, by Zyphra.
Capabilities
What ZUNA1.1 does.
Capability
Clinical relevance
Denoise channels
Removes muscle/eye-blink artifacts without losing signal
Reconstruct missing channels
Fixes dead electrodes, extends recordings from sparse montages
Upsample montages
Predicts 128-channel EEG from a standard 19-channel clinical recording
Channel-agnostic (3D scalp coordinates + time)
Works on any electrode layout via 4D rotary position encoding — no retraining per montage
Variable-length input (0.5–30s)
Handles short trial snippets and long continuous recordings with no reconfiguration
Planned clinical benchmarks
The following evaluations are planned, not yet completed: seizure detection (ictal vs. interictal vs. normal), artifact robustness under clinical noise, montage generalization (10-20, neonatal, intraoperative ECoG), pathology-aware denoising, and cross-dataset transfer beyond TUH.
Data Access
Temple University Hospital EEG Corpus.
The TUH EEG Corpus requires a data access request directly from Temple University. Once access is granted: place EDF files under data/tuh_raw/, run scripts/preprocess_tuh.py, and the output lands in data/tuh_processed/ as ZUNA-compatible pairs, ready for fine-tuning.
Recordings synced—
Data synced—
% of corpus—
Last sync—
This is a research pipeline, not a diagnostic tool. Outputs have not been validated for clinical decision-making and should not be used to diagnose or treat patients. The sync stats above are aggregate pipeline progress metrics only — no raw EEG data, file listings, or patient information is published here, per Temple University's data use agreement.
Quick Start
Fine-tune in five commands.
# Installgit clone https://github.com/eeg-medical/eeg-medical.git && cd eeg-medical
pip install -e ".[gpu]"# Download TUH EEG (requires Temple University access grant)python scripts/download_tuh.py --output data/tuh_raw# Preprocess into ZUNA-compatible formatpython scripts/preprocess_tuh.py --input data/tuh_raw --output data/tuh_processed# Fine-tune ZUNA1.1 on clinical EEGpython scripts/finetune.py --config configs/tuh_clinical_finetune.yaml
