Statements (17)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:speech_model
|
| gptkbp:availableOn |
gptkb:Hugging_Face_Model_Hub
|
| gptkbp:basedOn |
transformer architecture
|
| gptkbp:developedBy |
gptkb:Microsoft_Research
|
| gptkbp:language |
English
|
| gptkbp:notablePublication |
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
|
| gptkbp:relatedTo |
gptkb:Wav2Vec_2.0
gptkb:HuBERT |
| gptkbp:releaseYear |
2021
|
| gptkbp:supports |
self-supervised learning
|
| gptkbp:trainer |
large-scale audio datasets
|
| gptkbp:usedFor |
speech recognition
speech separation speaker verification |
| gptkbp:bfsParent |
gptkb:torchaudio
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
pre-trained WavLM models
|