<!-- 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
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: 0.4094
- Wer: 0.2825
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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.5419 | 3.45 | 500 | 1.2376 | 0.8772 |
0.5393 | 6.9 | 1000 | 0.4489 | 0.3894 |
0.1916 | 10.34 | 1500 | 0.3777 | 0.3185 |
0.1139 | 13.79 | 2000 | 0.4041 | 0.3058 |
0.0798 | 17.24 | 2500 | 0.3742 | 0.2988 |
0.0602 | 20.69 | 3000 | 0.3751 | 0.2897 |
0.0463 | 24.14 | 3500 | 0.4067 | 0.2865 |
0.0388 | 27.59 | 4000 | 0.4094 | 0.2825 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu102
- Datasets 1.18.3
- Tokenizers 0.11.6