wav2vec2-base-timit-demo-colab-3
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: 0.6622
- Wer: 0.5082
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: 10
- 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: 800
- num_epochs: 35
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.2195 | 8.77 | 500 | 0.9187 | 0.6635 |
| 0.5996 | 17.54 | 1000 | 0.6569 | 0.5347 |
| 0.2855 | 26.32 | 1500 | 0.6622 | 0.5082 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.11.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3