Tweeted By @MichaelAuli
Great progress in speech recognition: wav2vec 2.0 pre-training + self-training with just 10 minutes of labeled data rivals the best published systems trained on 960 hours of labeled data from just a year ago.
— Michael Auli (@MichaelAuli) October 26, 2020
Paper: https://t.co/niBzDiei1j
Models: https://t.co/frCK1GJMZQ pic.twitter.com/AjEWdna6J1