SynthGT Forced Alignment Experiments
Collection
A collection of the model checkpoints trained for singing-oriented forced alignment experiments. • 3 items • Updated
This checkpoint is a SOFA model trained on the English singing partition of 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 GTSinger dataset license.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support