|
--- |
|
license: mit |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
- LanceaKing/asvspoof2019 |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.7166781307466625 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8124204206436981 |
|
- name: Precision |
|
type: precision |
|
value: 0.9998169964543063 |
|
- name: Recall |
|
type: recall |
|
value: 0.6841833380294918 |
|
language: |
|
- en |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# VIT-ASVspoof2019-Mel_Spectrogram-Synthetic-Voice-Detection |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/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 |
