This model was trained from scratch on the librispeech_asr dataset. It achieves the following results on the evaluation set:
- Loss: 18.7898
- Wer: 1.0
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: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.5396 | 0.28 | 500 | 9.0401 | 1.0120 |
| 5.898 | 0.56 | 1000 | 9.3199 | 1.0 |
| 4.9595 | 0.84 | 1500 | 8.4434 | 1.4563 |
| 5.7082 | 1.12 | 2000 | 15.1805 | 1.0000 |
| 5.4377 | 1.4 | 2500 | 15.7984 | 1.0021 |
| 5.5941 | 1.68 | 3000 | 18.4928 | 1.0 |
| 5.0662 | 1.96 | 3500 | 17.4886 | 1.0000 |
| 4.8363 | 2.24 | 4000 | 18.9458 | 1.0 |
| 4.7908 | 2.52 | 4500 | 18.2794 | 1.0006 |
| 4.679 | 2.8 | 5000 | 18.7898 | 1.0 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0