Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
speech recognition model
|
| gptkbp:application |
automatic speech recognition
|
| gptkbp:architecture |
gptkb:convolutional_neural_network
|
| gptkbp:author |
gptkb:Steffen_Schneider
gptkb:Alexei_Baevski gptkb:Michael_Auli |
| gptkbp:basedOn |
deep learning
|
| gptkbp:citation |
2019
high |
| gptkbp:developedBy |
gptkb:Facebook_AI_Research
|
| gptkbp:firstReleased |
2019
|
| https://www.w3.org/2000/01/rdf-schema#label |
Wav2Vec
|
| gptkbp:input |
raw audio waveforms
|
| gptkbp:language |
English
|
| gptkbp:notablePublication |
gptkb:wav2vec:_Unsupervised_Pre-training_for_Speech_Recognition
|
| gptkbp:openSource |
true
|
| gptkbp:platform |
gptkb:PyTorch
|
| gptkbp:pretrainingMethod |
unsupervised
|
| gptkbp:repository |
https://github.com/pytorch/fairseq
|
| gptkbp:successor |
gptkb:Wav2Vec_2.0
|
| gptkbp:usedIn |
self-supervised learning
|
| gptkbp:bfsParent |
gptkb:Meta_AI
|
| gptkbp:bfsLayer |
5
|