Whisper openai-whisper-small
This model is a fine-tuned version of openai/whisper-small on the llamadas ecu911 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2243
- Wer: 48.5283
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: 2
- eval_batch_size: 1
- 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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6421 | 2.6596 | 500 | 0.9066 | 53.5438 |
| 0.1036 | 5.3191 | 1000 | 1.0305 | 50.4841 |
| 0.0184 | 7.9787 | 1500 | 1.1467 | 48.7413 |
| 0.0046 | 10.6383 | 2000 | 1.2243 | 48.5283 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1