|
--- |
|
license: apache-2.0 |
|
pipeline_tag: audio-classification |
|
|
|
base_model: alefiury/wav2vec2-large-xlsr-53-gender-recognition-librispeech |
|
--- |
|
This model is a fine tuning for the deepfake audio classification task. |
|
|
|
It achieves the following results on its evalutation data: |
|
|
|
* F1: 0.95 |
|
|
|
* Loss: 0.4056 |
|
|
|
It achieves the following results on [ASVspoof2019](https://www.kaggle.com/datasets/awsaf49/asvpoof-2019-dataset) evaluation subset: |
|
|
|
|
|
* Accuracy:0.9286 |
|
|
|
* Precision:0.9999 |
|
|
|
* Recall:0.9205 |
|
|
|
* F1-Score:0.9363 |
|
|
|
* Equal Error Rate (EER): 0.0401 |