Edit model card

wav2vec2-base-finetuned-gtzan-finetuned-gtzan

This model is a fine-tuned version of yuval6967/wav2vec2-base-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8942
  • Accuracy: 0.82

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.4822 0.9912 56 1.2225 0.78
0.3026 2.0 113 0.7599 0.85
0.2191 2.9912 169 0.8816 0.8
0.0791 4.0 226 1.1267 0.78
0.092 4.9912 282 0.8942 0.82

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
94.6M params
Tensor type
F32
·
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for koolaidoz/wav2vec2-base-finetuned-gtzan-finetuned-gtzan

Finetuned
(1)
this model

Dataset used to train koolaidoz/wav2vec2-base-finetuned-gtzan-finetuned-gtzan

Evaluation results