Whisper Small Ar- Martha:
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
Loss: 0.5854
Wer: 70.2071
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: 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: 500
mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9692 | 0.14 | 125 | 1.3372 | 173.0952 |
| 0.5716 | 0.29 | 250 | 0.9058 | 148.6795 |
| 0.3297 | 0.43 | 375 | 0.5825 | 63.6709 |
| 0.3083 | 0.57 | 500 | 0.5854 | 70.2071 |
Framework versions
Transformers 4.26.0.dev0
Pytorch 1.13.0+cu116
Datasets 2.7.1
Tokenizers 0.13.2