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: 0.83
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: 0.6771
- Accuracy: 0.83
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.0763 | 1.0 | 57 | 1.9012 | 0.54 |
| 3.2763 | 2.0 | 114 | 1.4578 | 0.69 |
| 2.5297 | 3.0 | 171 | 1.4215 | 0.56 |
| 1.9816 | 4.0 | 228 | 1.0966 | 0.66 |
| 1.7171 | 5.0 | 285 | 0.8921 | 0.76 |
| 1.4619 | 6.0 | 342 | 0.7647 | 0.82 |
| 1.3116 | 7.0 | 399 | 0.6880 | 0.85 |
| 1.1145 | 8.0 | 456 | 0.7591 | 0.77 |
| 0.7336 | 9.0 | 513 | 0.6362 | 0.85 |
| 0.6123 | 9.8319 | 560 | 0.6771 | 0.83 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0