|
--- |
|
base_model: facebook/wav2vec2 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- marsyas/gtzan |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: facebook/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: 0.4 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# facebook/wav2vec2-base-finetuned-gtzan |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2](https://huggingface.co/facebook/wav2vec2) on the GTZAN dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0140 |
|
- Accuracy: 0.4 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 0.96 | 6 | 2.2871 | 0.195 | |
|
| 2.2933 | 1.92 | 12 | 2.2658 | 0.18 | |
|
| 2.2933 | 2.88 | 18 | 2.2214 | 0.275 | |
|
| 2.2388 | 4.0 | 25 | 2.1885 | 0.29 | |
|
| 2.1455 | 4.96 | 31 | 2.1246 | 0.38 | |
|
| 2.1455 | 5.92 | 37 | 2.1139 | 0.35 | |
|
| 2.0823 | 6.88 | 43 | 2.0462 | 0.36 | |
|
| 2.0279 | 8.0 | 50 | 2.0282 | 0.405 | |
|
| 2.0279 | 8.96 | 56 | 2.0133 | 0.405 | |
|
| 1.9928 | 9.6 | 60 | 2.0140 | 0.4 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
