coml/spidr-vp20

SpidR VP-20

SpidR VP-20 is a SpidR model pretrained pretrained on a subset of 6k hours and 20 languages of VoxPopuli (all EU languages except English, French, and German) for the DiscoPhon benchmark. It was pretrained using the spidr library.

You can load it with:

from spidr.models import SpidR
from torch.hub import load_state_dict_from_url

state_dict = load_state_dict_from_url("https://huggingface.co/coml/spidr-vp20/resolve/main/final.pt")
model = SpidR().eval()
model.load_state_dict(state_dict)

Files:

• config.json: Model configuration.
• final.pt: Model checkpoint.
• full_checkpoint.pt: Full checkpoint, with model, optimizer, etc.

Citing

Please cite the DiscoPhon paper

@misc{poli2026discophon,
  title={{DiscoPhon}: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units},
  author={Maxime Poli and Manel Khentout and Angelo Ortiz Tandazo and Ewan Dunbar and Emmanuel Chemla and Emmanuel Dupoux},
  year={2026},
  eprint={2603.18612},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2603.18612},
}

along with SpidR.