safasaifudeen/whisper-base-safa

Whisper Base - Safa

This model is a fine-tuned version of openai/whisper-base on the medical-speech-transcription-and-intent dataset. It achieves the following results on the evaluation set:

• Loss: 0.1192
• Wer: 6.0619

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
0.0544	3.0030	1000	0.1282	7.2423
0.005	6.0060	2000	0.1124	6.0109
0.0006	9.0090	3000	0.1178	5.9891
0.0004	12.0120	4000	0.1192	6.0619

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1