Audio encoders from audio-embeddings: BEST-RQ, BEST-RQ-2 variants and Audio-JEPA, with pretrained checkpoints and Transformers loading.
Ludovic TUNCAY
ltuncay
AI & ML interests
None yet
Recent Activity
liked a model 2 days ago
qnguyen3/QUAN-Transcribe-1.0 updated a collection 3 days ago
BEST-RQ-2 family updated a model 3 days ago
ltuncay/Audio-JEPA-baseOrganizations
None yet
models 7
ltuncay/Audio-JEPA-base
Feature Extraction • 85.5M • Updated • 85
ltuncay/BEST-RQ-ViT
Feature Extraction • 85.5M • Updated • 43
ltuncay/BEST-RQ-2
Feature Extraction • 85.5M • Updated • 81 • 2
ltuncay/BEST-RQ-2.1-base
Feature Extraction • 85.5M • Updated • 60
ltuncay/BEST-RQ-2.2-base
Feature Extraction • 85.7M • Updated • 150
ltuncay/BEST-RQ-2.2-base-2M
Feature Extraction • 85.7M • Updated • 12
ltuncay/Audio-JEPA
Updated • 31 • 3
datasets 0
None public yet