metadata
tags:
- generated_from_trainer
datasets:
- librispeech_asr
model-index:
- name: ''
results: []
This model was trained from scratch on the librispeech_asr dataset. It achieves the following results on the evaluation set:
- Loss: 5.2346
- Wer: 1.9971
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: 0.001
- 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 |
|---|---|---|---|---|
| 5.4068 | 0.28 | 500 | 6.0935 | 1.9428 |
| 5.609 | 0.56 | 1000 | 6.0302 | 1.9717 |
| 5.5664 | 0.84 | 1500 | 5.6938 | 2.0066 |
| 4.9162 | 1.12 | 2000 | 5.6412 | 1.9733 |
| 4.9413 | 1.4 | 2500 | 5.5066 | 1.9556 |
| 4.7653 | 1.68 | 3000 | 5.3775 | 1.9548 |
| 4.566 | 1.96 | 3500 | 5.2843 | 1.9802 |
| 4.4488 | 2.24 | 4000 | 5.3816 | 1.9657 |
| 3.9933 | 2.52 | 4500 | 5.2800 | 1.9741 |
| 3.8714 | 2.8 | 5000 | 5.2346 | 1.9971 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0