TinyMyo: Tiny Foundation Model for EMG Signal Processing

📖 Overview

TinyMyo is a lightweight, Transformer-based foundation model designed specifically for surface electromyography (sEMG) signal processing. Unlike large-scale models, the TinyMyo family (including the 3.6M parameter base model and the ultra-compact 1.9M parameter TinyissimoMyo) is purpose-built for ultra-low-power edge deployment. It enables real-time motor intent decoding, neuromuscular assessment, and human-machine interaction directly on microcontrollers like the GAP9.

🚀 Key Highlights

• Generalist Foundation: Pre-trained on a massive, heterogeneous corpus of >480 GB of EMG data (NinaPro DB6/7, EMG2Pose) using self-supervised masked reconstruction.
• Edge-Ready: The first EMG foundation model demonstrated on an ultra-low-power MCU (GAP9), achieving sub-100ms inference for real-time applications.
• Highly Efficient: Just 3.6M parameters (1.9M for TinyissimoMyo), ensuring low latency and high energy efficiency (~45 mJ per inference).
• Versatile: Achieves state-of-the-art (SoA) performance across hand gesture classification, kinematic regression, and speech processing.

🧠 Model Architecture

• Core: 8-layer bidirectional Transformer encoder (4-layer for TinyissimoMyo).
• Embeddings: 192-dimensional latent space with 3 attention heads.
• Tokenization: Channel-independent patching (20 samples per patch) utilizing Rotary Position Embeddings (RoPE) to preserve temporal alignment across channels without spurious cross-channel ordering.
• Deployment: Optimized via offline liveness analysis, multi-level memory tiling, and INT8 fixed-point quantization for resource-constrained hardware execution.

📊 Performance Benchmarks

Task	Dataset	Metric	TinyMyo Result
Gesture Classification	NinaPro DB5	Accuracy	87.98%
Gesture Classification	EPN-612	Accuracy	96.57%
Gesture Classification	UCI EMG	Accuracy	97.10%
Gesture Classification	Generic Neuromotor Interface	CLER	0.142
Kinematic Regression	NinaPro DB8	MAE	8.8°
Speech Synthesis	Gaddy	WER	33.54%
Speech Recognition	Gaddy	WER	33.95%

⚡ Deployment (GAP9 MCU)

TinyMyo bridges the gap between high-performance deep learning and stringent wearable constraints. We provide two variants to balance the accuracy-latency trade-off:

TinyMyo (3.6M Parameters)

• Inference Time (5s window): 0.785 s
• Energy Consumption: 44.91 mJ
• Power Envelope: 57.18 mW

TinyissimoMyo (1.9M Parameters)

• Inference Time (5s window): 0.496 s
• Inference Time (1s window): 0.089 s (Sub-100ms regime, ideal for real-time prosthetic control)

🛠️ Getting Started

TinyMyo is part of theBioFoundation ecosystem.

Prerequisites

Install the required dependencies from the BioFoundation repository.

Loading & Fine-tuning

You can easily fine-tune the pre-trained weights for your specific task:

python run_train.py +experiment=TinyMyo_finetune pretrained_safetensors_path={*.safetensors}

📜 License & Citation

This model is licensed under CC BY-ND 4.0. If you find TinyMyo useful in your research, please cite our paper:

@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}
}