<!-- 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. -->
STT_Model_13
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: 6.2208
- Wer: 0.9857
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: 1e-06
- 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: 1000
- num_epochs: 100
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
No log | 5.13 | 200 | 173.3126 | 1.0008 |
No log | 10.26 | 400 | 144.4107 | 0.9992 |
34.9122 | 15.38 | 600 | 75.5557 | 0.9902 |
34.9122 | 20.51 | 800 | 23.4029 | 0.9857 |
12.437 | 25.64 | 1000 | 10.4605 | 0.9857 |
12.437 | 30.77 | 1200 | 9.0841 | 0.9857 |
12.437 | 35.9 | 1400 | 8.4492 | 0.9857 |
4.273 | 41.03 | 1600 | 7.9686 | 0.9857 |
4.273 | 46.15 | 1800 | 7.6086 | 0.9857 |
3.8969 | 51.28 | 2000 | 7.3133 | 0.9857 |
3.8969 | 56.41 | 2200 | 7.0270 | 0.9857 |
3.8969 | 61.54 | 2400 | 6.8339 | 0.9857 |
3.7169 | 66.67 | 2600 | 6.6504 | 0.9857 |
3.7169 | 71.79 | 2800 | 6.5280 | 0.9857 |
3.6442 | 76.92 | 3000 | 6.4103 | 0.9857 |
3.6442 | 82.05 | 3200 | 6.3444 | 0.9857 |
3.6442 | 87.18 | 3400 | 6.2852 | 0.9857 |
3.5493 | 92.31 | 3600 | 6.2478 | 0.9857 |
3.5493 | 97.44 | 3800 | 6.2208 | 0.9857 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2