---
license: cc-by-nc-sa-4.0
datasets:
- Silasimo/SynthGT
- AaronZ345/GTSinger
language:
- en
---

[![GitHub](https://img.shields.io/badge/GitHub-SOFA-black.svg)](https://github.com/qiuqiao/SOFA)
[![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-GTSinger-yellow)](https://huggingface.co/datasets/AaronZ345/GTSinger)
[![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-SynthGT-yellow)](https://huggingface.co/datasets/Silasimo/SynthGT)
[![GitHub](https://img.shields.io/badge/GitHub-SynthGT-black.svg)](https://github.com/SilasAntonisen/SynthGT)

This checkpoint is a [SOFA](https://github.com/qiuqiao/SOFA) model trained on our synthetic solo-singing dataset, [SynthGT](https://huggingface.co/datasets/Silasimo/SynthGT), and the English singing partition of [GTSinger](https://huggingface.co/datasets/AaronZ345/GTSinger),
for singing-oriented forced alignment experiments in our work "Synthesizing Ground Truth Phoneme Boundaries with SynthGT: A Synthetically Generated Solo-Singing Dataset".
To learn more about this work, check out our GitHub repo, or the SynthGT repo here on Hugging Face. An associated paper is currently under review.

We release this checkpoint under a cc-by-nc-sa-4.0 license in accordance with the SynthGT and GTSinger licenses.