metadata
library_name: transformers
license: apache-2.0
base_model: yuval6967/wav2vec2-base-finetuned-gtzan
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-gtzan-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-finetuned-gtzan
This model is a fine-tuned version of yuval6967/wav2vec2-base-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.1628
- 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: 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2026 | 0.9956 | 112 | 1.2365 | 0.78 |
| 0.3141 | 2.0 | 225 | 1.0698 | 0.8 |
| 0.0457 | 2.9956 | 337 | 0.9390 | 0.84 |
| 0.1295 | 4.0 | 450 | 1.1925 | 0.82 |
| 0.0108 | 4.9956 | 562 | 0.9958 | 0.86 |
| 0.1734 | 6.0 | 675 | 1.5863 | 0.75 |
| 0.0067 | 6.9956 | 787 | 0.9112 | 0.85 |
| 0.2115 | 8.0 | 900 | 1.0695 | 0.83 |
| 0.0061 | 8.9956 | 1012 | 1.1494 | 0.82 |
| 0.0038 | 9.9556 | 1120 | 1.1628 | 0.83 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1