MSR_UFormers / README.md
yongyizang's picture
Update README.md
ae66d47 verified
---
license: apache-2.0
---
# Music Restoration with UFormer
These checkpoints accompany the Music Source Restoration paper. (arxiv link coming soon)
A simple audio restoration toolkit based on UFormer, designed for music source restoration across different instrument groups. Supports long-file inference via overlap-add and multiple checkpoints for specialized restoration (e.g., guitars, vocals, synth).
## Directory Structure
```bash
music-restoration/ # Root of the repository
β”œβ”€β”€ model.py # UFormerConfig & UFormer definitions
β”œβ”€β”€ inference.py # Inference entry-point (CLI, HF API, Gradio)
β”œβ”€β”€ requirements.txt # Dependencies: torch, soundfile, gradio, huggingface_hub
β”œβ”€β”€ .gitattributes # LFS tracking for checkpoints
β”œβ”€β”€ README.md
└── checkpoints/ # Pretrained weights
β”œβ”€β”€ acoustic_guitar.pth
β”œβ”€β”€ bass.pth
β”œβ”€β”€ electric_guitar.pth
β”œβ”€β”€ guitars.pth
β”œβ”€β”€ keyboards.pth
β”œβ”€β”€ orchestra.pth
β”œβ”€β”€ rhythm_section.pth
β”œβ”€β”€ synth.pth
└── vocals.pth
```
## Installation
```bash
pip install -r requirements.txt
```
## Usage
### Command-Line Interface
```bash
python inference.py \
--input noisy.wav \
--output restored.wav \
--checkpoint guitars
```
### Hugging Face Inference API
Send a JSON payload:
```json
{
"inputs": <raw WAV bytes>,
"parameters": { "checkpoint": "vocals" }
}
```
### Gradio Demo (Spaces)
```bash
python inference.py --serve
```
Open the provided local URL to upload audio and select a checkpoint.
## Checkpoints
Available models for different instrument groups:
* `acoustic_guitar`
* `bass`
* `electric_guitar`
* `guitars`
* `keyboards`
* `orchestra`
* `rhythm_section`
* `synth`
* `vocals`
## License
Apache 2.0 License. See [LICENSE](LICENSE) for details.