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: 0.72
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: 1.2556
- Accuracy: 0.72
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2793 | 0.99 | 28 | 2.1814 | 0.28 |
| 1.9466 | 1.98 | 56 | 1.9110 | 0.41 |
| 1.7147 | 2.97 | 84 | 1.7353 | 0.47 |
| 1.5161 | 4.0 | 113 | 1.5839 | 0.53 |
| 1.3164 | 4.99 | 141 | 1.4552 | 0.62 |
| 1.2924 | 5.98 | 169 | 1.4023 | 0.68 |
| 1.1274 | 6.97 | 197 | 1.3962 | 0.65 |
| 1.0276 | 8.0 | 226 | 1.2685 | 0.74 |
| 0.967 | 8.99 | 254 | 1.2464 | 0.72 |
| 0.9227 | 9.91 | 280 | 1.2556 | 0.72 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3