whisper-medium-atco2-asr
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7769
- Wer: 23.9769
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-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5002 | 12.5 | 50 | 0.6266 | 23.6655 |
| 0.0013 | 25.0 | 100 | 0.6931 | 21.6637 |
| 0.0004 | 37.5 | 150 | 0.7297 | 21.7082 |
| 0.0003 | 50.0 | 200 | 0.7492 | 21.8416 |
| 0.0002 | 62.5 | 250 | 0.7622 | 21.8861 |
| 0.0002 | 75.0 | 300 | 0.7703 | 21.9306 |
| 0.0002 | 87.5 | 350 | 0.7753 | 23.0872 |
| 0.0002 | 100.0 | 400 | 0.7769 | 23.9769 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.0