---
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
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# whisper-tiny-finetuned-gtzan

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6420
- 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: 0.0001
- 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_steps: 10
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.9835        | 0.33  | 37   | 1.4610          | 0.62     |
| 1.5031        | 0.65  | 74   | 1.1531          | 0.63     |
| 1.1644        | 0.98  | 111  | 0.8526          | 0.73     |
| 0.9035        | 1.31  | 148  | 0.8748          | 0.69     |
| 0.7942        | 1.64  | 185  | 0.7811          | 0.78     |
| 0.8435        | 1.96  | 222  | 0.8262          | 0.7      |
| 0.5999        | 2.29  | 259  | 0.6450          | 0.72     |
| 0.6187        | 2.62  | 296  | 0.6616          | 0.79     |
| 0.6329        | 2.95  | 333  | 0.6479          | 0.81     |
| 0.3549        | 3.27  | 370  | 0.6246          | 0.78     |
| 0.3362        | 3.6   | 407  | 0.5348          | 0.81     |
| 0.3329        | 3.93  | 444  | 0.4657          | 0.85     |
| 0.2224        | 4.26  | 481  | 0.4433          | 0.89     |
| 0.208         | 4.58  | 518  | 0.6448          | 0.84     |
| 0.1983        | 4.91  | 555  | 0.6080          | 0.86     |
| 0.1736        | 5.24  | 592  | 0.6201          | 0.86     |
| 0.0976        | 5.57  | 629  | 0.6952          | 0.87     |
| 0.025         | 5.89  | 666  | 0.5872          | 0.9      |
| 0.0509        | 6.22  | 703  | 0.5845          | 0.91     |
| 0.1474        | 6.55  | 740  | 0.6800          | 0.89     |
| 0.0594        | 6.88  | 777  | 0.6280          | 0.87     |
| 0.0023        | 7.2   | 814  | 0.6850          | 0.88     |
| 0.0058        | 7.53  | 851  | 0.6766          | 0.89     |
| 0.023         | 7.86  | 888  | 0.8498          | 0.87     |
| 0.0272        | 8.19  | 925  | 0.7815          | 0.86     |
| 0.0011        | 8.51  | 962  | 0.6570          | 0.9      |
| 0.0012        | 8.84  | 999  | 0.6395          | 0.91     |
| 0.023         | 9.17  | 1036 | 0.6412          | 0.91     |
| 0.0009        | 9.5   | 1073 | 0.6416          | 0.91     |
| 0.001         | 9.82  | 1110 | 0.6420          | 0.91     |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3