|
gptkbp:instanceOf
|
speech recognition model
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:author
|
gptkb:Abdelrahman_Mohamed
gptkb:Alexei_Baevski
gptkb:Michael_Auli
gptkb:Yuhao_Zhou
|
|
gptkbp:availableOn
|
gptkb:GitHub
|
|
gptkbp:basedOn
|
self-supervised learning
|
|
gptkbp:citation
|
high
|
|
gptkbp:developedBy
|
gptkb:Facebook_AI_Research
|
|
gptkbp:fineTuning
|
supervised
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Wav2Vec 2.0
|
|
gptkbp:input
|
raw audio waveforms
|
|
gptkbp:language
|
English
|
|
gptkbp:notableFor
|
state-of-the-art performance in speech recognition
|
|
gptkbp:notablePublication
|
gptkb:wav2vec_2.0:_A_Framework_for_Self-Supervised_Learning_of_Speech_Representations
|
|
gptkbp:openSource
|
true
|
|
gptkbp:platform
|
gptkb:PyTorch
|
|
gptkbp:predecessor
|
gptkb:Wav2Vec
|
|
gptkbp:preTraining
|
self-supervised
|
|
gptkbp:publicationDate
|
gptkb:NeurIPS_2020
|
|
gptkbp:releaseYear
|
2020
|
|
gptkbp:trainer
|
gptkb:LibriSpeech
|
|
gptkbp:usedFor
|
automatic speech recognition
|
|
gptkbp:usedIn
|
ASR systems
speech-to-text applications
|
|
gptkbp:bfsParent
|
gptkb:Meta_AI
|
|
gptkbp:bfsLayer
|
5
|