wav2vec2-minds14-audio-classification-all
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: 2.6367
- Accuracy: 0.0973
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 |
|---|---|---|---|---|
| 2.6374 | 0.9951 | 51 | 2.6375 | 0.0894 |
| 2.6347 | 1.9902 | 102 | 2.6334 | 0.0900 |
| 2.6352 | 2.9854 | 153 | 2.6323 | 0.0930 |
| 2.6282 | 4.0 | 205 | 2.6280 | 0.0924 |
| 2.6224 | 4.9951 | 256 | 2.6398 | 0.0894 |
| 2.6122 | 5.9902 | 307 | 2.6306 | 0.0912 |
| 2.6225 | 6.9854 | 358 | 2.6325 | 0.0906 |
| 2.6196 | 8.0 | 410 | 2.6358 | 0.0961 |
| 2.6154 | 8.9951 | 461 | 2.6357 | 0.0924 |
| 2.6028 | 9.9512 | 510 | 2.6367 | 0.0973 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1