Wav2Vec2_SmallDataset
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6162
- Wer: 0.3740
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.5616 | 3.07 | 500 | 2.0020 | 1.0762 |
| 0.878 | 6.13 | 1000 | 0.5624 | 0.5165 |
| 0.3494 | 9.2 | 1500 | 0.5125 | 0.4560 |
| 0.214 | 12.27 | 2000 | 0.5534 | 0.4208 |
| 0.1392 | 15.34 | 2500 | 0.5376 | 0.4031 |
| 0.1062 | 18.4 | 3000 | 0.5784 | 0.3974 |
| 0.0816 | 21.47 | 3500 | 0.5700 | 0.3940 |
| 0.0614 | 24.54 | 4000 | 0.6174 | 0.3821 |
| 0.049 | 27.61 | 4500 | 0.6162 | 0.3740 |
Framework versions
- Transformers 4.17.0
- Pytorch 2.5.1+cu121
- Datasets 1.18.3
- Tokenizers 0.20.3