| --- |
| license: cc-by-nc-sa-4.0 |
| datasets: |
| - AaronZ345/GTSinger |
| language: |
| - en |
| --- |
| [](https://github.com/wolfgitpr/HubertFA) |
| [](https://huggingface.co/datasets/AaronZ345/GTSinger) |
| [](https://huggingface.co/datasets/Silasimo/SynthGT) |
| [](https://github.com/SilasAntonisen/SynthGT) |
|
|
| This checkpoint is a [HubertFA](https://github.com/wolfgitpr/HubertFA) model trained on [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 similar to the GTSinger dataset. |
|
|
| If you use this model, SynthGT, or other related resources, please cite: |
|
|
| ``` |
| bibtex |
| @unpublished{Antonisen2026SynthGT, |
| author = {Silas Antonisen and Iván López-Espejo}, |
| title = {Synthesizing Ground Truth Phoneme Boundaries with SynthGT: A Synthetically Generated Solo-Singing Corpus}, |
| note = {Submitted to IEEE Transactions on Audio, Speech and Language Processing}, |
| year = {2026} |
| } |
| ``` |
