<!-- 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. -->
This model was trained from scratch on the librispeech_asr dataset. It achieves the following results on the evaluation set:
- Loss: 0.7177
- Wer: 0.1283
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 25.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.1228 | 1.68 | 1500 | 6.0490 | 1.1433 |
| 5.4173 | 3.36 | 3000 | 5.3453 | 1.4878 |
| 4.1635 | 5.04 | 4500 | 4.4185 | 0.9644 |
| 2.1246 | 6.73 | 6000 | 3.2089 | 0.5026 |
| 1.88 | 8.41 | 7500 | 1.9886 | 0.3438 |
| 1.2606 | 10.09 | 9000 | 1.4472 | 0.2487 |
| 0.7492 | 11.77 | 10500 | 1.1716 | 0.1949 |
| 0.8868 | 13.45 | 12000 | 1.0146 | 0.1702 |
| 0.5078 | 15.13 | 13500 | 0.8821 | 0.1548 |
| 0.4515 | 16.82 | 15000 | 0.8181 | 0.1417 |
| 0.3902 | 18.5 | 16500 | 0.7765 | 0.1364 |
| 0.3575 | 20.18 | 18000 | 0.7367 | 0.1333 |
| 0.2903 | 21.86 | 19500 | 0.7211 | 0.1301 |
| 0.2698 | 23.54 | 21000 | 0.7177 | 0.1283 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0
