wav2vec2-base-ks-2sec
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: 0.0880
- Accuracy: 0.9822
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 | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.5003 | 1.0 | 399 | 0.9643 | 0.4284 |
| 0.1868 | 2.0 | 798 | 0.9748 | 0.1628 |
| 0.1413 | 3.0 | 1197 | 0.9796 | 0.1128 |
| 0.1021 | 4.0 | 1596 | 0.9813 | 0.0940 |
| 0.1089 | 5.0 | 1995 | 0.0880 | 0.9822 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.14.0
- Tokenizers 0.10.3