wav2vec2-base-version3
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: 0.4587
- Accuracy: 0.8410
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 |
|---|---|---|---|---|
| 1.0686 | 1.0 | 904 | 0.6588 | 0.7787 |
| 0.9816 | 2.0 | 1808 | 0.5031 | 0.8199 |
| 0.9203 | 3.0 | 2712 | 0.4819 | 0.8293 |
| 0.8399 | 4.0 | 3616 | 0.4800 | 0.8310 |
| 0.9001 | 5.0 | 4520 | 0.4587 | 0.8410 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0