whisper-small-ar-12hrsdarijadata-April29
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9985
- Wer: 77.7026
- Cer: 48.3376
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-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.8036 | 0.38 | 250 | 1.4314 | 92.8372 | 55.4587 |
| 1.3528 | 0.75 | 500 | 1.1339 | 79.2413 | 48.2563 |
| 1.1316 | 1.13 | 750 | 1.0272 | 76.8802 | 49.5272 |
| 1.1439 | 1.51 | 1000 | 0.9985 | 77.7026 | 48.3376 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.1.dev0
- Tokenizers 0.13.3