Update README.md
Browse files
README.md
CHANGED
@@ -6,21 +6,23 @@ pipeline_tag: audio-classification
|
|
6 |
|
7 |
base_model: alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech
|
8 |
---
|
9 |
-
This model is a fine tuning for the deepfake audio classification task
|
10 |
|
11 |
It achieves the following results on its evalutation data:
|
12 |
|
13 |
-
F1: 0.95
|
14 |
|
15 |
-
Loss: 0.4056
|
16 |
|
17 |
It achieves the following results on [ASVspoof2019](https://www.kaggle.com/datasets/awsaf49/asvpoof-2019-dataset) evaluation subset:
|
18 |
|
19 |
|
20 |
-
Accuracy:0.9286
|
21 |
|
22 |
-
Precision:0.9999
|
23 |
|
24 |
-
Recall:0.9205
|
25 |
|
26 |
-
F1-Score:0.9363
|
|
|
|
|
|
6 |
|
7 |
base_model: alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech
|
8 |
---
|
9 |
+
This model is a fine tuning for the deepfake audio classification task.
|
10 |
|
11 |
It achieves the following results on its evalutation data:
|
12 |
|
13 |
+
* F1: 0.95
|
14 |
|
15 |
+
* Loss: 0.4056
|
16 |
|
17 |
It achieves the following results on [ASVspoof2019](https://www.kaggle.com/datasets/awsaf49/asvpoof-2019-dataset) evaluation subset:
|
18 |
|
19 |
|
20 |
+
* Accuracy:0.9286
|
21 |
|
22 |
+
* Precision:0.9999
|
23 |
|
24 |
+
* Recall:0.9205
|
25 |
|
26 |
+
* F1-Score:0.9363
|
27 |
+
|
28 |
+
* Equal Error Rate (EER): 0.0401
|