VoxPopuli
Collection
A collection of open-source artefacts (datasets + checkpoints) from the first VoxPopuli release.
•
32 items
•
Updated
•
4
Facebook's Wav2Vec2 base model pretrained on the 10k unlabeled subset of VoxPopuli corpus.
Authors: Changhan Wang, Morgane Riviere, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux from Facebook AI
See the official website for more information, here
Please refer to this blog on how to fine-tune this model on a specific language. Note that you should replace "facebook/wav2vec2-large-xlsr-53"
with this checkpoint for fine-tuning.