Hemg/small-deepfake

Source: 🤗audio-classificationapache-2.095M params378 MBsafetensors✓ 20 checksumsupdated 963d ago

small-deepfake

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.7489
Accuracy: 0.5

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: 0.0003
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8	1	0.6871	0.5
No log	1.6	2	0.7041	0.5
No log	2.4	3	0.7126	0.5
No log	3.2	4	0.7489	0.5

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Weights

Original

F32378 MB
2 files
model.safetensors 378 MBtraining_args.bin 4.9 kB

Seed this model

Have the files? Submit a torrent.

Submit a torrent

Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Hemg/small-deepfake ./model-folder