Release date and specs of Meta's AI model
Unsupervised speech-recognition approach requiring no transcriptions.
- Released
- May 21, 2021
- Context window
- —
- Modality
- audiotext
- Open source
- —
- API available
- —
- Releases
- 1
Releases
May 21, 2021wav2vec-U publishedResearch paper
Facebook AI introduced unsupervised speech recognition using unpaired speech audio and text.
wav2vec-U FAQ
When was wav2vec-U released?
wav2vec-U was released by Meta on May 21, 2021.
Which model family does wav2vec-U belong to?
wav2vec-U is part of the wav2vec model family by Meta.

