W2V-BERT 2.0
JSON →A self-supervised speech representation model from Facebook combining wav2vec 2.0 and BERT for audio understanding.
Capabilities
open-weights
Dates
releasedJun 2024
Resources
API
full doc /v1/models/facebook/w2v-bert-2.0
A self-supervised speech representation model from Facebook combining wav2vec 2.0 and BERT for audio understanding.