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-2
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: 0.8
wav2vec2-base-finetuned-gtzan-2
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: 0.7182
- Accuracy: 0.8
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: 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: 9
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9471 | 1.0 | 90 | 1.9127 | 0.44 |
| 1.3728 | 2.0 | 180 | 1.4732 | 0.52 |
| 1.4239 | 3.0 | 270 | 1.4735 | 0.55 |
| 0.8211 | 4.0 | 360 | 1.0095 | 0.73 |
| 0.9167 | 5.0 | 450 | 0.8899 | 0.71 |
| 0.5153 | 6.0 | 540 | 0.7832 | 0.76 |
| 0.6258 | 7.0 | 630 | 0.7073 | 0.79 |
| 0.3004 | 8.0 | 720 | 0.6175 | 0.85 |
| 0.2903 | 9.0 | 810 | 0.7182 | 0.8 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1