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: 0.88
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: 0.5242
- 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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.5894 | 1.0 | 56 | 0.6959 | 0.87 |
| 0.5636 | 1.99 | 112 | 0.7488 | 0.82 |
| 0.4387 | 2.99 | 168 | 0.7051 | 0.83 |
| 0.3296 | 4.0 | 225 | 0.6642 | 0.86 |
| 0.3094 | 5.0 | 281 | 0.6453 | 0.85 |
| 0.2881 | 5.99 | 337 | 0.6484 | 0.84 |
| 0.2712 | 6.99 | 393 | 0.5738 | 0.86 |
| 0.267 | 8.0 | 450 | 0.5593 | 0.86 |
| 0.1794 | 9.0 | 506 | 0.5699 | 0.86 |
| 0.2602 | 9.96 | 560 | 0.5242 | 0.88 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3