Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ tags:
|
|
| 5 |
- CLAP
|
| 6 |
- audio classification
|
| 7 |
- zero-shot classification
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# tinyCLAP: Distilling Contrastive Language-Audio Pretrained models
|
|
@@ -83,7 +84,10 @@ A list of available models with their computational cost is described in the fol
|
|
| 83 |
|
| 84 |
| alpha | beta | t0 | N | Params [M] | ESC-50 | UrbanSound8K | TUT17 |
|
| 85 |
|:-----:|:----:|:--:|:-:|:----------:|:------:|:------------:|:-----:|
|
| 86 |
-
| 1.5 | 0.75 | 6 | 7 | 4.4 |
|
|
|
|
|
|
|
|
|
|
| 87 |
|
| 88 |
## Citing tinyCLAP
|
| 89 |
|
|
|
|
| 5 |
- CLAP
|
| 6 |
- audio classification
|
| 7 |
- zero-shot classification
|
| 8 |
+
library_name: speechbrain
|
| 9 |
---
|
| 10 |
|
| 11 |
# tinyCLAP: Distilling Contrastive Language-Audio Pretrained models
|
|
|
|
| 84 |
|
| 85 |
| alpha | beta | t0 | N | Params [M] | ESC-50 | UrbanSound8K | TUT17 |
|
| 86 |
|:-----:|:----:|:--:|:-:|:----------:|:------:|:------------:|:-----:|
|
| 87 |
+
| 1.5 | 0.75 | 6 | 7 | 4.4 | 76.3% | 69.4% | 21.8% |
|
| 88 |
+
|
| 89 |
+
**Note**: I am currently computing the confidence intervals for these results. Numbers might be slightly different from the ones reported in the paper.
|
| 90 |
+
The original paper's checkpoints are available through [this link](https://www.dropbox.com/scl/fi/e3aj76vxwlb4w6hs3mclv/tinyCLAP_results.zip?rlkey=7fl426tz1vf686oyosvja8i9s&dl=0).
|
| 91 |
|
| 92 |
## Citing tinyCLAP
|
| 93 |
|