metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: wav2vec2-base-finetuned-ks
    results:
      - task:
          name: DeepFake audio detection
          type: audio-classification
        dataset:
          name: Fake or Real
          type: Audio
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9994443415447305
language:
  - en
library_name: transformers
pipeline_tag: audio-classification

wav2vec2-base-finetuned-ks

This model is a fine-tuned version of facebook/wav2vec2-base on the Fake or Real (FoR) dataset. It achieves the following results on the evaluation set:

Loss: 0.0031
Accuracy: 0.9994

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0085	1.0	421	0.0133	0.9977
0.0005	2.0	842	0.0060	0.9986
0.0002	3.0	1263	0.0031	0.9994
0.0002	4.0	1684	0.0033	0.9993
0.0001	5.0	2105	0.0028	0.9994

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2