Farhang87/whisper-large-turbo-medical

Whisper Large Turbo Medical

This model is a fine-tuned version of openai/whisper-large-turbo on the Medical ASR dataset. It achieves the following results on the evaluation set:

• Loss: 0.0672
• Wer: 4.3447

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: 32
• 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: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2994	0.5405	100	0.2101	9.9928
0.1405	1.0811	200	0.1212	5.7929
0.0859	1.6216	300	0.0929	4.4895
0.044	2.1622	400	0.0739	3.9585
0.0248	2.7027	500	0.0672	4.3447

Framework versions

• Transformers 4.49.0
• Pytorch 2.4.0+cu121
• Datasets 3.3.2
• Tokenizers 0.21.0