README.md

metadata

library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
model-index:
  - name: wav2vec2-base-finetuned-gtzan
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: GTZAN
          type: marsyas/gtzan
          config: all
          split: train
          args: all
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7307692307692307

wav2vec2-base-finetuned-gtzan

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

• Loss: 1.2479
• Accuracy: 0.7308

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: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 18
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9797	1.0	70	1.9644	0.3718
1.4254	2.0	140	1.7058	0.4359
1.3827	3.0	210	1.3349	0.5769
1.1156	4.0	280	1.2080	0.6795
0.7843	5.0	350	1.1072	0.6667
0.7063	6.0	420	1.2091	0.6667
0.4972	7.0	490	1.0370	0.7179
0.6555	8.0	560	1.1193	0.6795
0.4934	9.0	630	0.9080	0.7692
0.1664	10.0	700	1.2513	0.6795
0.3892	11.0	770	1.3065	0.6667
0.0895	12.0	840	1.2479	0.7308

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0