santhosh643/whisper-small-en

whisper_fine_tune_Nataraj

This model is a fine-tuned version of openai/whisper-small on the Medical Speech, Transcription, and Intent dataset. It achieves the following results on the evaluation set:

• Loss: 0.1956
• Wer: 12.6737

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 600
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5559	0.2825	100	0.5252	15.9811
0.1575	0.5650	200	0.2096	11.5990
0.1228	0.8475	300	0.2005	11.1729
0.0528	1.1299	400	0.1967	11.6732
0.0402	1.4124	500	0.1960	12.3680
0.0583	1.6949	600	0.1956	12.6737

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1