Whisper Medium Medical
This model is a fine-tuned version of openai/whisper-medium on the Medical ASR dataset. It achieves the following results on the evaluation set:
- Loss: 0.0995
- Wer: 12.4065
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: 8
- 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: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7532 | 0.1357 | 100 | 0.2695 | 13.0099 |
| 0.2155 | 0.2714 | 200 | 0.2053 | 9.8238 |
| 0.2392 | 0.4071 | 300 | 0.1567 | 8.9549 |
| 0.151 | 0.5427 | 400 | 0.1159 | 6.9273 |
| 0.1439 | 0.6784 | 500 | 0.0995 | 12.4065 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 79
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for jilangdi/whisper-medium-medical
Base model
openai/whisper-medium