<!-- 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-sah
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: 0.4177
- Wer: 0.4480
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.3675 | 4.5 | 500 | 2.2690 | 1.0 |
| 0.8695 | 9.01 | 1000 | 0.4878 | 0.5811 |
| 0.3469 | 13.51 | 1500 | 0.4021 | 0.4973 |
| 0.2236 | 18.02 | 2000 | 0.4299 | 0.4750 |
| 0.1685 | 22.52 | 2500 | 0.4266 | 0.4612 |
| 0.1383 | 27.03 | 3000 | 0.4177 | 0.4480 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
