TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge

TinyMyo is a 3.6M-parameter Transformer foundation model for surface EMG (sEMG), optimized for ultra-low-power edge deployment (GAP9 MCU). It demonstrates state-of-the-art performance across gesture classification, kinematic regression, and speech synthesis.

---

🚀 Quick Start

TinyMyo is built as a specialized model within the BioFoundation framework.

1. Requirements

• Preprocessing: Dependencies for data scripts are in scripts/requirements.txt.
• BioFoundation: Full framework requirements for training/inference are in the GitHub repository.

2. Preprocessing

Process raw datasets into HDF5 format:

python scripts/db5.py --data_dir $DATA_PATH/raw/ --save_dir $DATA_PATH/h5/ --seq_len 200 --stride 50

See scripts/README.md for all dataset commands.

3. Fine-tuning

python run_train.py +experiment=TinyMyo_finetune pretrained_safetensors_path=/path/to/base.safetensors

---

🧠 Architecture & Pretraining

• Core: 8-layer Transformer encoder (192-dim embeddings, 3 heads).
• Tokenization: Channel-independent patching (20 samples/patch) with RoPE.
• Data: Pretrained on >480 GB of EMG (NinaPro DB6/7, EMG2Pose).
• Specs: 3.6M parameters, 4.0 GFLOPs.

🎯 Benchmarks

Task	Dataset	Metric	TinyMyo
Gesture	NinaPro DB5	Accuracy	89.41%
Gesture	EPN-612	Accuracy	96.74%
Gesture	UCI EMG	Accuracy	97.56%
Regression	NinaPro DB8	MAE	8.77°
Speech	Gaddy (Speech Synthesis)	WER	33.54%
Speech	Gaddy (Speech Recognition)	WER	33.95%

---

⚡ Edge Performance (GAP9 MCU)

• Inference: 0.785 s
• Energy: 44.91 mJ
• Power: 57.18 mW

---

📜 License & Citation

Weights are licensed under CC BY-ND 4.0. See LICENSE for details.

@misc{fasulo2026tinymyotinyfoundationmodel,
      title={TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge},
      author={Matteo Fasulo and Giusy Spacone and Thorir Mar Ingolfsson and Yawei Li and Luca Benini and Andrea Cossettini},
      year={2026},
      eprint={2512.15729},
      archivePrefix={arXiv},
      primaryClass={eess.SP},
      url={https://arxiv.org/abs/2512.15729},
}