whisper-medium-23
This model is a fine-tuned version of saif-daoud/whisper-medium-22 on the afrispeech-200 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4774
- Wer: 0.5625
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: 8
- 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: 750
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8977 | 0.5 | 375 | 0.6403 | 0.1715 |
| 0.6345 | 1.5 | 750 | 0.4774 | 0.5625 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3