Thien Tran's picture

8 3 12

Thien Tran

gaunernst

·

gau-nernst

AI & ML interests

None yet

Organizations

None yet

gaunernst's activity

New activity in gaunernst/vit_base_patch16_1024_128.audiomae_as2m_ft_as20k 2 months ago

Embedding model

#3 opened 2 months ago by

New activity in facebook/data2vec-audio-large 3 months ago

pretraining dataset is Libri-Light, not LibriSpeech

#2 opened 3 months ago by

New activity in facebook/dinov2-base 5 months ago

Image size mismatch (518 vs 224)

#9 opened 5 months ago by

New activity in laion/CLIP-ViT-B-16-DataComp.XL-s13B-b90K 7 months ago

Add instructions on how to use this with timm (i.e. show timm model tag)

#1 opened 7 months ago by

New activity in laion/clap-htsat-unfused about 1 year ago

Use most recent checkpoints

#2 opened over 1 year ago by

New activity in facebook/encodec_32khz about 1 year ago

Where does this model come from?

#1 opened about 1 year ago by

New activity in MIT/ast-finetuned-audioset-10-10-0.4593 about 1 year ago

How do you convert pre-trained models to HF standard?

#4 opened over 1 year ago by

New activity in asapp/sew-d-tiny-100k about 1 year ago

Does this model use attention mask?

#2 opened about 1 year ago by