Audio-WestlakeU/audiossl
A library built for easier audio self-supervised training, downstream tasks evaluation
PythonNOASSERTION
Issues
- 0
Unexpected background voice is detected.
#15 opened by Alien1007 - 12
Hello, may I ask if ATST Frame can publicly disclose the models and scripts used for inference?
#12 opened by Angelalilyer - 1
issue on ckpt loading in train_distill.py
#14 opened by folkartist - 6
Share the training log
#11 opened by hbellafkir - 8
Congrats to your new version!
#8 opened by daisukelab - 3
- 1
- 2
Extracting embeddings.
#6 opened by Sreeni1204 - 2
not found 'assl' package.
#4 opened by kimsojeong1225 - 2
- 1