pre-trained wav2vec2 models

URI: https://gptkb.org/entity/pre-trained_wav2vec2_models
GPTKB entity
Statements (36)
Predicate Object
gptkbp:instanceOf gptkb:model
speech recognition model
gptkbp:architecture gptkb:transformation
gptkbp:author gptkb:Abdelrahman_Mohamed
gptkb:Alexei_Baevski
gptkb:Michael_Auli
gptkb:Yuhao_Zhou
gptkbp:availableOn gptkb:Hugging_Face_Model_Hub
gptkbp:basedOn wav2vec2 architecture
gptkbp:benchmarkPerformance state-of-the-art on LibriSpeech
gptkbp:developedBy gptkb:Facebook_AI_Research
gptkbp:fineTunedWith yes
gptkbp:firstReleased 2020
https://www.w3.org/2000/01/rdf-schema#label pre-trained wav2vec2 models
gptkbp:implementedIn gptkb:TensorFlow
gptkb:PyTorch
gptkbp:input raw audio waveform
gptkbp:license gptkb:MIT
gptkbp:notableVariant wav2vec2-base
wav2vec2-large
wav2vec2-large-960h
wav2vec2-xlsr-53
gptkbp:openSource yes
gptkbp:output contextualized speech representations
gptkbp:pdf gptkb:wav2vec_2.0:_A_Framework_for_Self-Supervised_Learning_of_Speech_Representations
gptkbp:relatedTo gptkb:wav2vec
gptkb:HuBERT
Data2Vec
gptkbp:selfSupervised yes
gptkbp:supportsLanguage English
multiple languages
gptkbp:trainer large-scale speech datasets
gptkbp:usedFor automatic speech recognition
audio feature extraction
gptkbp:bfsParent gptkb:torchaudio
gptkbp:bfsLayer 6