joorock12/wav2vec2-large-xlsr-portuguese

The Wav2Vec2 model was proposed in the paper: A Framework for Self-Supervised Learning of Speech Representations by Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli. It is speech model that accepts a float array corresponding to the raw waveform of the speech signal. The model was trained using connectionist temporal classification (CTC).