W2v-BERT
Google BrainMassachusetts Institute of Technology (MIT)Speech recognition (ASR)
Developed by Google Brain,Massachusetts Institute of Technology (MIT) in 2021, W2v-BERT is a Speech recognition (ASR) model with 1000000000.0 parameters.
About W2v-BERT
Motivated by the success of masked language modeling~(MLM) in pre-training natural language processing models, we propose w2v-BERT that explores MLM for self-supervised speech representation learning. w2v-BERT is a framework that combines contrastive
Details
- Provider
- Google Brain,Massachusetts Institute of Technology (MIT)
- Task
- Speech recognition (ASR)
- Parameters
- 1000000000.0
- Released
- 2021-08-07
- Open weights
- No