metadata
license: apache-2.0
base_model: saketag73/classification_facebook_wav2vec2-base-finetuned-gtzan-2
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
metrics:
- name: Accuracy
type: accuracy
value: 0.805
wav2vec2-base-finetuned-gtzan
This model is a fine-tuned version of saketag73/classification_facebook_wav2vec2-base-finetuned-gtzan-2 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.7271
- Accuracy: 0.805
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: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0116 | 1.0 | 25 | 1.0805 | 0.715 |
| 0.7603 | 2.0 | 50 | 1.0321 | 0.76 |
| 0.6462 | 3.0 | 75 | 0.8840 | 0.775 |
| 0.5343 | 4.0 | 100 | 0.8303 | 0.78 |
| 0.4705 | 5.0 | 125 | 0.9837 | 0.72 |
| 0.3806 | 6.0 | 150 | 0.8099 | 0.79 |
| 0.3126 | 7.0 | 175 | 0.7897 | 0.79 |
| 0.2727 | 8.0 | 200 | 0.6896 | 0.81 |
| 0.2301 | 9.0 | 225 | 0.7518 | 0.81 |
| 0.2138 | 10.0 | 250 | 0.7271 | 0.805 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2