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: 0.88
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: 0.6411
- Accuracy: 0.88
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: 6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 13
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8965 | 1.0 | 113 | 1.8976 | 0.28 |
| 1.3295 | 2.0 | 226 | 1.4744 | 0.52 |
| 1.159 | 3.0 | 339 | 1.0918 | 0.66 |
| 0.5861 | 4.0 | 452 | 0.9779 | 0.74 |
| 1.0464 | 5.0 | 565 | 0.9167 | 0.73 |
| 0.8294 | 6.0 | 678 | 0.8404 | 0.75 |
| 0.462 | 7.0 | 791 | 0.8323 | 0.78 |
| 0.1366 | 8.0 | 904 | 0.7485 | 0.8 |
| 0.179 | 9.0 | 1017 | 0.6523 | 0.87 |
| 0.0361 | 10.0 | 1130 | 0.6313 | 0.87 |
| 0.2355 | 11.0 | 1243 | 0.6609 | 0.88 |
| 0.0543 | 12.0 | 1356 | 0.6559 | 0.88 |
| 0.0201 | 13.0 | 1469 | 0.6411 | 0.88 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0