Release date and specs of Meta's AI model
Self-supervised speech representation model trained directly from raw audio.
- Released
- Jun 21, 2019
- Context window
- —
- Modality
- audio
- Open source
- —
- API available
- —
- Releases
- 1
Releases
Jun 21, 2019wav2vec publishedResearch paper
Facebook AI introduced wav2vec, a self-supervised approach to speech representation learning from raw audio.
wav2vec FAQ
When was wav2vec released?
wav2vec was released by Meta on Jun 21, 2019.
Which model family does wav2vec belong to?
wav2vec is part of the wav2vec model family by Meta.

