wav2vec2-base-finetuned-minds
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: 2.6976
- Accuracy: 0.0531
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6297 | 1.0 | 113 | 2.6709 | 0.0619 |
| 2.6756 | 2.0 | 226 | 2.6744 | 0.0619 |
| 2.6513 | 3.0 | 339 | 2.6692 | 0.0619 |
| 2.6578 | 4.0 | 452 | 2.6733 | 0.0619 |
| 2.5932 | 5.0 | 565 | 2.6724 | 0.0619 |
| 2.6251 | 6.0 | 678 | 2.6706 | 0.0619 |
| 2.6301 | 7.0 | 791 | 2.6743 | 0.0619 |
| 2.6573 | 8.0 | 904 | 2.6879 | 0.0531 |
| 2.6232 | 9.0 | 1017 | 2.6935 | 0.0619 |
| 2.6479 | 10.0 | 1130 | 2.6976 | 0.0531 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1