whisper-tiny-finetuned-minds14-en-v2
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6804
- Wer Ortho: 0.3362
- Wer: 0.3353
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0014 | 1.79 | 50 | 0.6437 | 0.3708 | 0.3648 |
| 0.0012 | 3.57 | 100 | 0.6664 | 0.3461 | 0.3353 |
| 0.0113 | 5.36 | 150 | 0.6338 | 0.3374 | 0.3353 |
| 0.0021 | 7.14 | 200 | 0.6466 | 0.3467 | 0.3453 |
| 0.0013 | 8.93 | 250 | 0.6690 | 0.3399 | 0.3383 |
| 0.0006 | 10.71 | 300 | 0.6804 | 0.3362 | 0.3353 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3