whisper-small-en-notpretrained
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: 5.2550
- Wer: 103.2792
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.8761 | 0.0166 | 1000 | 5.6410 | 100.5027 |
| 5.5313 | 0.0332 | 2000 | 5.3679 | 104.4272 |
| 5.4119 | 0.0497 | 3000 | 5.2869 | 114.7152 |
| 5.4158 | 0.0663 | 4000 | 5.2550 | 103.2792 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.20.1