STT_Model_7
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: 0.6921
- Wer: 0.3465
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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 20.0 | 200 | 2.9402 | 1.0 |
| No log | 40.0 | 400 | 2.8466 | 1.0 |
| 3.4486 | 60.0 | 600 | 0.6408 | 0.4648 |
| 3.4486 | 80.0 | 800 | 0.5779 | 0.4141 |
| 0.2246 | 100.0 | 1000 | 0.6921 | 0.3465 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2