|
|
--- |
|
|
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 |
|
|
|
