wav2vec2-minds14-audio-classification-en
This model is a fine-tuned version of anton-l/wav2vec2-base-ft-keyword-spotting on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6639
- Accuracy: 0.0796
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 | 0.8 | 3 | 2.6727 | 0.0531 |
| No log | 1.8667 | 7 | 2.6503 | 0.0531 |
| 2.6417 | 2.9333 | 11 | 2.6485 | 0.0796 |
| 2.6417 | 4.0 | 15 | 2.6514 | 0.0531 |
| 2.6417 | 4.8 | 18 | 2.6531 | 0.0442 |
| 2.6189 | 5.8667 | 22 | 2.6596 | 0.0619 |
| 2.6189 | 6.9333 | 26 | 2.6650 | 0.0531 |
| 2.6123 | 8.0 | 30 | 2.6639 | 0.0796 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1