|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- audiofolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2musicgenre |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# wav2musicgenre |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4377 |
|
- Accuracy: 0.5175 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.8985 | 0.99 | 70 | 1.9125 | 0.3493 | |
|
| 1.7093 | 1.99 | 141 | 1.6999 | 0.4356 | |
|
| 1.6057 | 3.0 | 212 | 1.6076 | 0.4683 | |
|
| 1.5392 | 4.0 | 283 | 1.5730 | 0.4958 | |
|
| 1.5228 | 4.99 | 353 | 1.4994 | 0.5029 | |
|
| 1.4261 | 5.99 | 424 | 1.4647 | 0.5131 | |
|
| 1.3901 | 7.0 | 495 | 1.4556 | 0.5126 | |
|
| 1.3677 | 8.0 | 566 | 1.4461 | 0.5175 | |
|
| 1.3309 | 8.99 | 636 | 1.4430 | 0.5153 | |
|
| 1.3152 | 9.89 | 700 | 1.4377 | 0.5175 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
