wav2vec2-base-timit-demo-colab7
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: 1.1687
- Wer: 0.6478
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 60
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.8409 | 7.04 | 500 | 3.1487 | 1.0 |
| 2.6259 | 14.08 | 1000 | 1.5598 | 0.8730 |
| 1.083 | 21.13 | 1500 | 1.0600 | 0.7347 |
| 0.6061 | 28.17 | 2000 | 1.0697 | 0.7006 |
| 0.4022 | 35.21 | 2500 | 1.0617 | 0.6913 |
| 0.2884 | 42.25 | 3000 | 1.1962 | 0.6768 |
| 0.225 | 49.3 | 3500 | 1.1753 | 0.6567 |
| 0.1852 | 56.34 | 4000 | 1.1687 | 0.6478 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.11.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3