Jabberjay
Collection
🦜 Synthetic Voice Detection • 15 items • Updated • 2
Image Classification
Transformers
TensorBoard
Safetensors
English
vit
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("MattyB95/VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection")
model = AutoModelForImageClassification.from_pretrained("MattyB95/VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection")Quick Links
VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.0649
- Accuracy: 0.7167
- F1: 0.8124
- Precision: 0.9998
- Recall: 0.6842
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.007 | 1.0 | 3173 | 0.0108 | 0.9972 | 0.9984 | 0.9969 | 1.0 |
| 0.0015 | 2.0 | 6346 | 0.0022 | 0.9997 | 0.9998 | 0.9999 | 0.9998 |
| 0.0 | 3.0 | 9519 | 0.0025 | 0.9996 | 0.9998 | 0.9997 | 0.9999 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 4,144
Model tree for MattyB95/VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection
Base model
google/vit-base-patch16-224-in21kDataset used to train MattyB95/VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection
Collection including MattyB95/VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection
Evaluation results
- Accuracy on imagefoldervalidation set self-reported0.717
- F1 on imagefoldervalidation set self-reported0.812
- Precision on imagefoldervalidation set self-reported1.000
- Recall on imagefoldervalidation set self-reported0.684
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="MattyB95/VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")