<!-- 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-nsc-demo-3
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4681
- Wer: 0.1933
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: 100
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6872 | 2.27 | 50 | 0.3920 | 0.2365 |
| 0.3487 | 4.55 | 100 | 0.3700 | 0.2129 |
| 0.2121 | 6.82 | 150 | 0.4308 | 0.2202 |
| 0.1737 | 9.09 | 200 | 0.4114 | 0.2051 |
| 0.1378 | 11.36 | 250 | 0.4674 | 0.2084 |
| 0.114 | 13.64 | 300 | 0.4989 | 0.2162 |
| 0.0885 | 15.91 | 350 | 0.4914 | 0.1998 |
| 0.097 | 18.18 | 400 | 0.4597 | 0.1986 |
| 0.0694 | 20.45 | 450 | 0.4933 | 0.1996 |
| 0.0747 | 22.73 | 500 | 0.4690 | 0.1963 |
| 0.0792 | 25.0 | 550 | 0.4619 | 0.1963 |
| 0.0646 | 27.27 | 600 | 0.4691 | 0.1951 |
| 0.0604 | 29.55 | 650 | 0.4681 | 0.1933 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
