---
library_name: transformers
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: ast-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: 0.94
    - name: Precision
      type: precision
      value: 0.946171802054155
    - name: Recall
      type: recall
      value: 0.9379426129426129
    - name: F1
      type: f1
      value: 0.9379839011750775
---

<!-- 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. -->

# ast-finetuned-gtzan

This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3551
- Accuracy: 0.94
- Precision: 0.9462
- Recall: 0.9379
- F1: 0.9380

## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.9185        | 1.0   | 113  | 0.6489          | 0.78     | 0.8099    | 0.7976 | 0.7743 |
| 0.473         | 2.0   | 226  | 0.6660          | 0.8      | 0.8284    | 0.8208 | 0.7963 |
| 0.4124        | 3.0   | 339  | 0.6544          | 0.8      | 0.8237    | 0.8002 | 0.7880 |
| 0.1625        | 4.0   | 452  | 0.4139          | 0.86     | 0.8519    | 0.8603 | 0.8454 |
| 0.2298        | 5.0   | 565  | 0.5540          | 0.88     | 0.8689    | 0.8694 | 0.8618 |
| 0.1091        | 6.0   | 678  | 0.4291          | 0.89     | 0.8933    | 0.8935 | 0.8855 |
| 0.0208        | 7.0   | 791  | 0.4161          | 0.91     | 0.9200    | 0.9000 | 0.8977 |
| 0.0181        | 8.0   | 904  | 0.3769          | 0.92     | 0.9133    | 0.9202 | 0.9127 |
| 0.0035        | 9.0   | 1017 | 0.3431          | 0.94     | 0.9353    | 0.9424 | 0.9371 |
| 0.013         | 10.0  | 1130 | 0.3551          | 0.94     | 0.9462    | 0.9379 | 0.9380 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1