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: 0.91
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:
- Accuracy: 0.91
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4667 | 1.0 | 113 | 0.7013 | 0.79 |
| 0.6329 | 2.0 | 226 | 1.1081 | 0.69 |
| 0.151 | 3.0 | 339 | 0.6619 | 0.84 |
| 0.2903 | 4.0 | 452 | 0.8713 | 0.78 |
| 0.379 | 5.0 | 565 | 0.7113 | 0.85 |
| 0.1222 | 6.0 | 678 | 0.6789 | 0.87 |
| 0.292 | 7.0 | 791 | 0.6808 | 0.88 |
| 0.0305 | 8.0 | 904 | 0.5518 | 0.91 |
| 0.0073 | 9.0 | 1017 | 0.7742 | 0.88 |
| 0.007 | 10.0 | 1130 | 0.7251 | 0.88 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3