wav2vec2-base-version2
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: 0.5021
- Accuracy: 0.8289
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 |
|---|---|---|---|---|
| 1.2113 | 1.0 | 453 | 0.8686 | 0.7241 |
| 1.0923 | 2.0 | 906 | 0.6201 | 0.7887 |
| 1.0072 | 3.0 | 1359 | 0.5494 | 0.8067 |
| 0.98 | 4.0 | 1813 | 0.5145 | 0.8187 |
| 0.906 | 5.0 | 2265 | 0.5021 | 0.8289 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0