LeonM78Code/whisper-small-dv

Whisper Small Dv - Leon Lee

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4909
• Wer Ortho: 53.6249
• Wer: 9.9384

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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: 100
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0162	6.4935	500	0.2193	57.3020	11.4285
0.0027	12.9870	1000	0.2799	55.4287	10.4983
0.0013	19.4805	1500	0.3227	55.2824	10.5105
0.0007	25.9740	2000	0.3129	54.6069	10.4149
0.0	32.4675	2500	0.3903	53.6249	9.9680
0.0	38.9610	3000	0.4478	53.6945	9.9332
0.0	45.4545	3500	0.4796	53.6458	9.9524
0.0	51.9481	4000	0.4909	53.6249	9.9384

Framework versions

• Transformers 4.48.1
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0