<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-base_toy_train_data_random_high_pass
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: 1.2841
- Wer: 0.7222
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.061 | 2.1 | 500 | 3.0551 | 1.0 |
| 1.1294 | 4.2 | 1000 | 1.3102 | 0.8777 |
| 0.7051 | 6.3 | 1500 | 1.2081 | 0.8092 |
| 0.5421 | 8.4 | 2000 | 1.2280 | 0.7684 |
| 0.448 | 10.5 | 2500 | 1.2459 | 0.7506 |
| 0.3777 | 12.6 | 3000 | 1.3533 | 0.7631 |
| 0.3611 | 14.7 | 3500 | 1.2058 | 0.7291 |
| 0.3177 | 16.81 | 4000 | 1.3168 | 0.7185 |
| 0.279 | 18.91 | 4500 | 1.2841 | 0.7222 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.11.0+cu102
- Datasets 2.0.0
- Tokenizers 0.11.6
