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: default
split: train
args: default
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: 0.7770
- 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 11
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0152 | 1.0 | 112 | 1.9017 | 0.52 |
| 1.6232 | 2.0 | 225 | 1.5400 | 0.53 |
| 1.2989 | 3.0 | 337 | 1.1494 | 0.65 |
| 1.2035 | 4.0 | 450 | 1.1189 | 0.69 |
| 0.6804 | 5.0 | 562 | 0.8873 | 0.69 |
| 0.7305 | 6.0 | 675 | 0.7527 | 0.81 |
| 0.4738 | 7.0 | 787 | 0.6880 | 0.78 |
| 0.2824 | 8.0 | 900 | 0.7893 | 0.73 |
| 0.3863 | 9.0 | 1012 | 0.5786 | 0.85 |
| 0.4061 | 10.0 | 1125 | 0.7070 | 0.81 |
| 0.1302 | 11.0 | 1237 | 0.5829 | 0.88 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3