whisper-small-dv

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5722
• Wer Ortho: 0.3023
• Wer: 0.3011

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: 16
• 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: constant_with_warmup
• lr_scheduler_warmup_steps: 2
• training_steps: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
No log	0.0714	2	0.5676	0.3140	0.3158
No log	0.1429	4	0.5642	0.3054	0.3076
No log	0.2143	6	0.5657	0.3004	0.3017
No log	0.2857	8	0.5681	0.3023	0.3034
No log	0.3571	10	0.5722	0.3023	0.3011

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0+cpu
• Datasets 3.1.0
• Tokenizers 0.20.3