Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Ubenwa
/
sb-ecapa-vggsound
like
1
Follow
Ubenwa
10
Audio Classification
speechbrain
PyTorch
VGGSound
English
embeddings
Sound
ECAPA-TDNN
TDNN
arxiv:
2106.04624
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
3ae5129
sb-ecapa-vggsound
1 contributor
History:
5 commits
gorinars
model trained with regular softmax added
3ae5129
almost 2 years ago
.gitattributes
1.64 kB
v2 model with noise augmentation and longer training
almost 2 years ago
CKPT.yaml
98 Bytes
v2 model with noise augmentation and longer training
almost 2 years ago
classifier.ckpt
526 kB
LFS
model trained with regular softmax added
almost 2 years ago
config.json
52 Bytes
model added
almost 2 years ago
embedding_model.ckpt
83.3 MB
LFS
model trained with regular softmax added
almost 2 years ago
hyperparams.yaml
1.65 kB
model trained with regular softmax added
almost 2 years ago
label_encoder.txt
8.06 kB
model added
almost 2 years ago
normalizer.ckpt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.LongStorage"
What is a pickle import?
1.13 kB
LFS
v2 model with noise augmentation and longer training
almost 2 years ago
test.py
235 Bytes
model added
almost 2 years ago