Jaesung Huh
commited on
Commit
•
8cc9463
1
Parent(s):
491b9bd
add caveat
Browse files- .gitignore +1 -0
- README.md +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
.DS_Store
|
README.md
CHANGED
|
@@ -57,6 +57,9 @@ I used the pretrained ECAPA-TDNN from [TaoRuijie's](https://github.com/TaoRuijie
|
|
| 57 |
|
| 58 |
The model achieved **98.7%** accuracy on the VoxCeleb1 identification test split.
|
| 59 |
|
|
|
|
|
|
|
|
|
|
| 60 |
## Reference
|
| 61 |
- [Original github repository](https://github.com/JaesungHuh/voice-gender-classifier)
|
| 62 |
- I modified the model architecture from [TaoRuijie's](https://github.com/TaoRuijie/ECAPA-TDNN) repository.
|
|
|
|
| 57 |
|
| 58 |
The model achieved **98.7%** accuracy on the VoxCeleb1 identification test split.
|
| 59 |
|
| 60 |
+
## Caveat
|
| 61 |
+
I would like to note the training dataset I've used for this model (VoxCeleb) may not represent the global human population. Please be careful of unintended biases when using this model.
|
| 62 |
+
|
| 63 |
## Reference
|
| 64 |
- [Original github repository](https://github.com/JaesungHuh/voice-gender-classifier)
|
| 65 |
- I modified the model architecture from [TaoRuijie's](https://github.com/TaoRuijie/ECAPA-TDNN) repository.
|