metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
model-index:
  - name: whisper-tiny-finetuned-gtzan
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: GTZAN
          type: marsyas/gtzan
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.88

whisper-tiny-finetuned-gtzan

This model is a fine-tuned version of openai/whisper-tiny on the GTZAN dataset. It achieves the following results on the evaluation set:

Loss: 0.8859
Accuracy: 0.88

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
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7103	1.0	113	1.4757	0.57
0.8805	2.0	226	0.8030	0.74
0.7231	3.0	339	0.4844	0.88
0.9119	4.0	452	0.6392	0.79
0.2952	5.0	565	0.5729	0.83
0.1099	6.0	678	0.5263	0.83
0.1363	7.0	791	0.4978	0.91
0.0021	8.0	904	0.6480	0.89
0.0413	9.0	1017	0.7381	0.87
0.0023	10.0	1130	0.6896	0.9
0.0006	11.0	1243	0.7574	0.89
0.1621	12.0	1356	0.8407	0.88
0.0005	13.0	1469	0.7967	0.89
0.0005	14.0	1582	0.7795	0.89
0.0004	15.0	1695	0.7795	0.9
0.0003	16.0	1808	0.9152	0.87
0.0003	17.0	1921	0.8594	0.88
0.0003	18.0	2034	0.8481	0.88
0.0003	19.0	2147	0.8471	0.88
0.0545	20.0	2260	0.8859	0.88

Framework versions

Transformers 4.33.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3