Hemg/deeepfake-audio-16

Source: 🤗audio-classificationapache-2.095M params378 MBsafetensors✓ 13 checksumsupdated 952d ago

deeepfake-audio-16

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: 0.6954
Accuracy: 0.4624

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: 0.0005
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
lr_scheduler_warmup_ratio: 0.01
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7063	1.0	46	0.6956	0.5376
0.6997	2.0	92	0.6953	0.4624
0.697	3.0	138	0.6955	0.4624
0.6964	4.0	184	0.6954	0.4624

Framework versions

Transformers 4.39.3
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/deeepfake-audio-16 ./model-folder