Whisper Tiny en - ld76
This model is a fine-tuned version of openai/whisper-tiny on the Minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8795
- Wer Ortho: 0.3577
- Wer: 0.3616
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: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0006 | 17.54 | 500 | 0.7812 | 0.3419 | 0.3477 |
| 0.0 | 35.09 | 1000 | 0.8306 | 0.3267 | 0.3319 |
| 0.0 | 52.63 | 1500 | 0.8573 | 0.3570 | 0.3610 |
| 0.0 | 70.18 | 2000 | 0.8795 | 0.3577 | 0.3616 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3
- Downloads last month
- 9