whisper-synthesized-turkish-deneme-2
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: 0.6205
- Wer: 85.8473
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-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: 500
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.9831 | 1.04 | 50 | 1.9347 | 46.2053 |
| 1.7562 | 2.08 | 100 | 1.5724 | 43.7232 |
| 1.4051 | 3.12 | 150 | 1.2677 | 35.7160 |
| 1.0484 | 4.17 | 200 | 0.8637 | 90.9905 |
| 0.7046 | 5.21 | 250 | 0.6794 | 100.5967 |
| 0.5857 | 6.25 | 300 | 0.6205 | 85.8473 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3