Hugging Face's logo

speechbrain
/
vit-base-esc50

English
Sound Classification
Interpretable Sound Classification
Activation Maps Thresholding
ViT
Model card Files Community
lucadellalib commited on
Commit
e8a8f9c
•
1 Parent(s): 285c510

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ This repository provides the pretrained model to perform audio classification wi
20
 
21
  | Release | Accuracy (%) | Training time | GPUs |
22
  |:----------:|:------------:|:------------------:|:-----------:|
23
- | 01-16-24 | 73.6 | 56 seconds / epoch | 1xV100 32GB |
24
 
25
  Please, take a look at the [reference paper](https://arxiv.org/abs/2402.02754) for more info. You can find the training recipe in SpeechBrain [here](https://github.com/speechbrain/speechbrain/tree/develop/recipes/ESC50/interpret).
26
 
 
20
 
21
  | Release | Accuracy (%) | Training time | GPUs |
22
  |:----------:|:------------:|:------------------:|:-----------:|
23
+ | 16-01-24 | 73.6 | 56 seconds / epoch | 1xV100 32GB |
24
 
25
  Please, take a look at the [reference paper](https://arxiv.org/abs/2402.02754) for more info. You can find the training recipe in SpeechBrain [here](https://github.com/speechbrain/speechbrain/tree/develop/recipes/ESC50/interpret).
26