metadata
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: 0.84
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: 0.6933
- Accuracy: 0.84
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1735 | 0.99 | 56 | 2.1378 | 0.24 |
| 1.7104 | 2.0 | 113 | 1.7187 | 0.52 |
| 1.3864 | 2.99 | 169 | 1.5629 | 0.53 |
| 1.1797 | 4.0 | 226 | 1.4349 | 0.62 |
| 1.0675 | 4.99 | 282 | 1.0705 | 0.74 |
| 0.9568 | 6.0 | 339 | 1.0412 | 0.74 |
| 0.7465 | 6.99 | 395 | 0.8219 | 0.84 |
| 0.6917 | 8.0 | 452 | 0.8743 | 0.78 |
| 0.4634 | 8.99 | 508 | 0.8266 | 0.81 |
| 0.4757 | 10.0 | 565 | 0.7233 | 0.86 |
| 0.4341 | 10.99 | 621 | 0.8024 | 0.81 |
| 0.3802 | 11.89 | 672 | 0.6933 | 0.84 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.0
- Datasets 2.18.0
- Tokenizers 0.15.2