Whisper Medium - Medical
This model is a fine-tuned version of openai/whisper-medium on the Voice Medical New dataset. It achieves the following results on the evaluation set:
- Loss: 0.2450
- Cer: 8.2235
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: 5e-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: 1000
- training_steps: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.4701 | 0.3861 | 1000 | 0.3794 | 13.8516 |
| 0.3279 | 0.7722 | 2000 | 0.3462 | 12.5011 |
| 0.2186 | 1.1583 | 3000 | 0.3031 | 11.2530 |
| 0.1489 | 1.5444 | 4000 | 0.2746 | 9.6823 |
| 0.1726 | 1.9305 | 5000 | 0.2415 | 8.8990 |
| 0.0459 | 2.3166 | 6000 | 0.2450 | 8.2235 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.