Whisper Small Sl - Padajno
This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3707
- Wer Ortho: 28.2066
- Wer: 25.9370
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: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.9497 | 0.6135 | 100 | 0.8683 | 37.6703 | 35.8745 |
| 0.171 | 1.2270 | 200 | 0.3742 | 33.4847 | 31.2039 |
| 0.1841 | 1.8405 | 300 | 0.3407 | 31.0585 | 28.7337 |
| 0.0592 | 2.4540 | 400 | 0.3492 | 29.5545 | 27.1153 |
| 0.0434 | 3.0675 | 500 | 0.3624 | 29.7106 | 27.2572 |
| 0.027 | 3.6810 | 600 | 0.3707 | 28.2066 | 25.9370 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0