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: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.8
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: 0.7966
- 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: 8
- eval_batch_size: 8
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.956 | 1.0 | 113 | 1.8269 | 0.48 |
| 1.3896 | 2.0 | 226 | 1.5206 | 0.53 |
| 1.1 | 3.0 | 339 | 1.1325 | 0.66 |
| 0.7254 | 4.0 | 452 | 1.1456 | 0.62 |
| 0.6099 | 5.0 | 565 | 0.8337 | 0.73 |
| 0.5452 | 6.0 | 678 | 0.8621 | 0.72 |
| 0.5286 | 7.0 | 791 | 0.6800 | 0.82 |
| 0.2849 | 8.0 | 904 | 0.8335 | 0.77 |
| 0.2248 | 9.0 | 1017 | 0.7541 | 0.8 |
| 0.0822 | 10.0 | 1130 | 0.7966 | 0.8 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2