---
license: cc0-1.0
---

# AEROMamba: Efficient Audio Super-Resolution
*AI-Generated README - Original: [GitHub](https://github.com/aeromamba-super-resolution/aeromamba) | [Demo](https://aeromamba-super-resolution.github.io/)*

---

## Model Overview
**Architecture**: Hybrid GAN + Mamba SSM  
**Task**: 11.025 kHz → 44.1 kHz audio upsampling  
**Key Improvements**:
- 14x faster inference vs AERO
- 5x less GPU memory usage
- 66.47 subjective score (vs AERO's 60.03)

**Checkpoint**: [MUSDB18-HQ Model](https://huggingface.co/KingNish/AEROMamba/blob/main/checkpoint.th)

---

## Quick Start
```python
# Installation
pip install torch==1.12.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
pip install causal-conv1d==1.1.2 mamba-ssm==1.1.3

# Inference
from src.models.aeromamba import AEROMamba
import torchaudio

model = AEROMamba.load_from_checkpoint("checkpoint.th")
lr_audio, sr = torchaudio.load("low_res.wav")  # 11kHz input
hr_audio = model(lr_audio)  # 44.1kHz output
```

---

## Performance (MUSDB18)
| Metric          | Low-Res | AERO  | AEROMamba |
|-----------------|---------|-------|-----------|
| ViSQOL ↑        | 1.82    | 2.90  | **2.93**  |
| LSD ↓           | 3.98    | 1.34  | **1.23**  |
| Subjective ↑    | 38.22   | 60.03 | **66.47** |

**Hardware**: 14x faster on RTX 3090 (0.087s vs 1.246s)

---

## Training Data
**MUSDB18-HQ**:
- 150 full-track music recordings
- 44.1 kHz originals → 11.025 kHz downsampled pairs
- 87.5/12.5 train-val split

---

## Citation
```bibtex
@inproceedings{Abreu2024lamir,
  author    = {Wallace Abreu and Luiz Wagner Pereira Biscainho},
  title     = {AEROMamba: Efficient Audio SR with GANs and SSMs},
  booktitle = {Proc. Latin American Music IR Workshop},
  year      = {2024}
}
```

*This README was AI-generated based on original project materials. For training code and OLA inference scripts, visit the [GitHub repo](https://github.com/aeromamba-super-resolution/aeromamba).*