metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-base-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: 0.782051282051282
wav2vec2-base-finetuned-gtzan
This model is a fine-tuned version of facebook/wav2vec2-base on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.0679
- Accuracy: 0.7821
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: 3e-05
- train_batch_size: 10
- eval_batch_size: 10
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0975 | 1.0 | 70 | 2.0767 | 0.3590 |
| 1.6787 | 2.0 | 140 | 1.7150 | 0.4872 |
| 1.5562 | 3.0 | 210 | 1.4839 | 0.4744 |
| 1.2489 | 4.0 | 280 | 1.4014 | 0.6026 |
| 0.9445 | 5.0 | 350 | 1.3975 | 0.5897 |
| 0.8189 | 6.0 | 420 | 1.0886 | 0.7179 |
| 0.6352 | 7.0 | 490 | 1.0411 | 0.6795 |
| 0.6983 | 8.0 | 560 | 1.0652 | 0.6795 |
| 0.4918 | 9.0 | 630 | 0.9020 | 0.7436 |
| 0.534 | 10.0 | 700 | 1.1106 | 0.7308 |
| 0.5065 | 11.0 | 770 | 0.8243 | 0.7821 |
| 0.1966 | 12.0 | 840 | 1.0750 | 0.7436 |
| 0.2377 | 13.0 | 910 | 1.0619 | 0.7564 |
| 0.1434 | 14.0 | 980 | 1.1533 | 0.7436 |
| 0.1128 | 15.0 | 1050 | 1.0679 | 0.7821 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0