srirama/whisper-small-hi

Whisper Small - D Notes

This model is a fine-tuned version of openai/whisper-small on the Sample Dental dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001
• Wer: 6.6841

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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0024	10.9890	1000	0.0010	7.0692
0.0002	21.9780	2000	0.0003	6.6687
0.0001	32.9670	3000	0.0001	6.6071
0.0001	43.9560	4000	0.0001	6.6841

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1