Whisper Small Hu - cleaned
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 hu cleaned dataset. It achieves the following results on the evaluation set:
- Loss: 0.0982
- Wer Ortho: 11.0788
- Wer: 10.2129
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: 1.25e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0904 | 1.33 | 200 | 0.1232 | 15.4117 | 14.4286 |
| 0.0316 | 2.66 | 400 | 0.0950 | 11.8467 | 10.9171 |
| 0.0136 | 3.99 | 600 | 0.0950 | 11.3208 | 10.4348 |
| 0.0047 | 5.32 | 800 | 0.0959 | 10.9079 | 10.0424 |
| 0.0029 | 6.64 | 1000 | 0.0982 | 11.0788 | 10.2129 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Downloads last month
- 3