wav2vec2-base-finetuned-digits
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: 0.0605
- Accuracy: 0.9846
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 |
|---|---|---|---|---|
| 0.4808 | 1.0 | 620 | 0.3103 | 0.9696 |
| 0.1877 | 2.0 | 1240 | 0.1043 | 0.9791 |
| 0.1478 | 3.0 | 1860 | 0.0727 | 0.9827 |
| 0.1611 | 4.0 | 2480 | 0.0644 | 0.9842 |
| 0.0993 | 5.0 | 3100 | 0.0605 | 0.9846 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1