descriptinc/lyrebird-wav2clip
Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP
PythonMIT
Issues
- 0
What is the exact CLIP model from CLIP paper that you used in pretraining phase?
#23 opened by nikifori - 0
Probably incorrect normalization?
#21 opened by xwhjy - 0
Different model other than ResNet-18?
#20 opened by BetelhemNebebe - 1
The details concerning loading raw audio files
#16 opened by jinx2018 - 2
request of projection layer weight
#19 opened by seungheondoh - 0
Supervised scenario no transform
#18 opened by alirezadir - 0
Integrated into VQGAN+CLIP 3D Zooming notebook
#17 opened by voodoohop - 0
Zero-shot audio classification
#15 opened by wsntxxn - 0
torch version
#14 opened by annahung31 - 1
dataset
#10 opened by zh794390558 - 0
- 0
train from scratch
#11 opened by zh794390558 - 1
Paper
#6 opened by EmreOzkose