Whisper maritime data (FINE-TUNED)
This model is a fine-tuned version of openai/whisper-small on the Bridge to Bridge Chatter (26694, 38117) dataset. It achieves the following results on the evaluation set:
- Loss: 4.5734
- Wer: 102.7571
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 OptimizerNames.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 |
|---|---|---|---|---|
| 0.0936 | 38.4615 | 1000 | 3.7551 | 107.7586 |
| 0.026 | 76.9231 | 2000 | 4.1906 | 103.2153 |
| 0.0126 | 115.3846 | 3000 | 4.4438 | 103.1765 |
| 0.0053 | 153.8462 | 4000 | 4.5734 | 102.7571 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for efaith2000/whisper-small-maritime
Base model
openai/whisper-small