2023-05-23
New work! The Massively Multilingual Speech (MMS) project scales speech technology to 1,100-4,000 languages using self-supervised learning with wav2vec 2.0. Paper: https://research.facebook.com/ ... Blog: https://ai.facebook.com/... Code/models: https://github.com/... [video]
MIT Technology Review
Meta unveils open-source AI models the company says can identify 4,000+ languages and produce speech for 1,000+ languages, a 40x and 10x increase, respectively
They could help lead to speech apps for many more languages than exist now. — Meta has built AI models that can recognize …
2021-05-22
Today we are announcing our work on building speech recognition models without any labeled data! wav2vec-U rivals some of the best supervised systems from only two years ago. Paper: https://ai.facebook.com/... Blog: https://ai.facebook.com/... Code: https://github.com/...
Engadget
Facebook's wav2vec Unsupervised, a way to build speech recognition systems that require no transcribed data, may bring automatic translations to more countries
Wav2vec Unsupervised (wav2vec-U) … Tiernan Ray / ZDNet : Facebook AI cuts by more than half the error rate of unsupervised speech recognition Donald Conway / Insider Voice : Facebo...
This shows how completely unsupervised speech recognition with wav2vec-U compares to the best supervised systems on the Librispeech benchmark over the past few years. https://twitter.com/...
Engadget
Facebook's wav2vec Unsupervised, a way to build speech recognition systems that require no transcribed data, may bring automatic translations to more countries
Wav2vec Unsupervised (wav2vec-U) … Tiernan Ray / ZDNet : Facebook AI cuts by more than half the error rate of unsupervised speech recognition Donald Conway / Insider Voice : Facebo...