<!-- 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-idrak-practice
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: 0.3538
- Wer: 0.3209
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.634 | 0.87 | 500 | 2.6452 | 1.0 |
1.0497 | 1.73 | 1000 | 0.5711 | 0.5138 |
0.4584 | 2.6 | 1500 | 0.4421 | 0.4492 |
0.3198 | 3.46 | 2000 | 0.3818 | 0.3941 |
0.2263 | 4.33 | 2500 | 0.3653 | 0.3767 |
0.1845 | 5.19 | 3000 | 0.3424 | 0.3661 |
0.1388 | 6.06 | 3500 | 0.3702 | 0.3519 |
0.1214 | 6.92 | 4000 | 0.3515 | 0.3439 |
0.1026 | 7.79 | 4500 | 0.3585 | 0.3292 |
0.0834 | 8.65 | 5000 | 0.3474 | 0.3236 |
0.0737 | 9.52 | 5500 | 0.3538 | 0.3209 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.12.0+cu116
- Datasets 1.18.3
- Tokenizers 0.12.1