wav2vec2-base-timit-demo-sol
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: 0.3922
- Wer: 0.2862
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: 64
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.6222 | 6.85 | 500 | 1.5843 | 0.9627 |
| 0.509 | 13.7 | 1000 | 0.4149 | 0.3417 |
| 0.1221 | 20.55 | 1500 | 0.3692 | 0.2992 |
| 0.0618 | 27.4 | 2000 | 0.3922 | 0.2862 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.1+cu102
- Datasets 1.18.3
- Tokenizers 0.12.1