metadata

language: 100k
tags:
  - audio
  - automatic-speech-recognition
  - voxpopuli
license: cc-by-nc-4.0

Wav2Vec2-Large-VoxPopuli

Facebook's Wav2Vec2 large model pretrained on the 100k subset of VoxPopuli corpus.

Paper: VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

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