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: all
          split: train
          args: all
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.91

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: 0.6142
Accuracy: 0.91

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
1.7559	1.0	113	1.6022	0.57
0.9793	2.0	226	0.9895	0.7
0.8508	3.0	339	0.6379	0.78
0.5114	4.0	452	0.8367	0.72
0.115	5.0	565	0.4465	0.88
0.0239	6.0	678	0.5796	0.85
0.2095	7.0	791	0.6141	0.87
0.0019	8.0	904	0.5765	0.88
0.0012	9.0	1017	0.5393	0.87
0.0013	10.0	1130	0.5126	0.92
0.0008	11.0	1243	0.4751	0.91
0.0006	12.0	1356	0.5002	0.91
0.0005	13.0	1469	0.4905	0.91
0.0006	14.0	1582	0.5577	0.91
0.0004	15.0	1695	0.6326	0.9
0.0004	16.0	1808	0.6188	0.92
0.0004	17.0	1921	0.6420	0.91
0.0003	18.0	2034	0.5999	0.91
0.0003	19.0	2147	0.6105	0.91
0.0003	20.0	2260	0.6142	0.91

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu118
Datasets 2.19.2
Tokenizers 0.19.1