metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: shimalabaudio-20240425
results: []
shimalabaudio-20240425
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6771
- Accuracy: 0.6154
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7566 | 1.0 | 4 | 0.7434 | 0.3846 |
| 0.7194 | 2.0 | 8 | 0.7631 | 0.3846 |
| 0.5906 | 3.0 | 12 | 0.7569 | 0.3846 |
| 0.5716 | 4.0 | 16 | 0.7512 | 0.3846 |
| 0.5623 | 5.0 | 20 | 0.7445 | 0.3846 |
| 0.5372 | 6.0 | 24 | 0.7418 | 0.3846 |
| 0.6806 | 7.0 | 28 | 0.7226 | 0.3846 |
| 0.5049 | 8.0 | 32 | 0.6937 | 0.6154 |
| 0.6707 | 9.0 | 36 | 0.6861 | 0.6154 |
| 0.4769 | 10.0 | 40 | 0.6771 | 0.6154 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.12.0
- Tokenizers 0.15.1