<!-- 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. -->
wav2vec2-base-timit-demo-colab
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: 0.3958
- Wer: 0.2801
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: 32
- 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.4101 | 3.45 | 500 | 1.0402 | 0.7472 |
| 0.5156 | 6.9 | 1000 | 0.4003 | 0.3554 |
| 0.1906 | 10.34 | 1500 | 0.4068 | 0.3158 |
| 0.114 | 13.79 | 2000 | 0.3930 | 0.3049 |
| 0.0791 | 17.24 | 2500 | 0.4465 | 0.3020 |
| 0.0578 | 20.69 | 3000 | 0.3998 | 0.2905 |
| 0.0451 | 24.14 | 3500 | 0.4089 | 0.2874 |
| 0.0375 | 27.59 | 4000 | 0.3958 | 0.2801 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2
