Whisper Small Tr - Saadin
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:
- Wer: 23.18
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: 16
- 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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Validation Loss | Wer |
|---|---|---|---|
| 0.17 | 1000 | 0.2572 | 23.18 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1
- Datasets 2.5.3.dev0
- Tokenizers 0.12.1