wav2vec2-base-finetuned-ks
This model is a fine-tuned version of facebook/wav2vec2-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.0895
- Accuracy: 0.9832
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6834 | 1.0 | 399 | 0.6010 | 0.8954 |
| 0.307 | 2.0 | 798 | 0.1814 | 0.9750 |
| 0.1782 | 3.0 | 1197 | 0.1134 | 0.9829 |
| 0.1732 | 4.0 | 1597 | 0.0974 | 0.9819 |
| 0.122 | 5.0 | 1995 | 0.0895 | 0.9832 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2