whisper-large-v2-medical-9

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1386

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.2381	20	0.5954
0.9678	0.4762	40	0.3312
0.372	0.7143	60	0.1767
0.1657	0.9524	80	0.1568
0.1297	1.1905	100	0.1507
0.1297	1.4286	120	0.1455
0.0923	1.6667	140	0.1403
0.0974	1.9048	160	0.1376
0.0753	2.1429	180	0.1389
0.053	2.3810	200	0.1396
0.053	2.6190	220	0.1384
0.0601	2.8571	240	0.1386

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.0+cu121
• Datasets 2.18.0
• Tokenizers 0.20.1