# Load model directly
from transformers import AutoProcessor, AutoModelForAudioClassification
processor = AutoProcessor.from_pretrained("Hemgg/Deepfake-audio-detection")
model = AutoModelForAudioClassification.from_pretrained("Hemgg/Deepfake-audio-detection", device_map="auto")Quick Links
deeepfake-audio-Recognition
This model is a fine-tuned version of facebook/wav2vec2-base on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2288
- Accuracy: 0.9545
Model description
- The model is fintune on facebook/wav2vec2-base
Intended uses & limitations
- The model still needs dataset to increase model accuracy.
Training and evaluation data
- The model is trained on multi-ethnic english dataset.
- The input audio dataset is about 16KHz.
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 290
Model tree for Hemgg/Deepfake-audio-detection
Spaces using Hemgg/Deepfake-audio-detection 16
Evaluation results
- Accuracy on audiofolderself-reported0.955
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="Hemgg/Deepfake-audio-detection")