whisper-small-dv

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

• Loss: 0.1554
• Wer Ortho: 10.6904
• Wer: 10.4262

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use adamw_torch_fused 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: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.6708	0.1252	100	0.1903	12.1169	11.8410
0.6569	0.2503	200	0.1734	11.3655	11.1424
0.5969	0.3755	300	0.1599	10.9839	10.7608
0.5591	0.5006	400	0.1573	10.6552	10.3792
0.5645	0.6258	500	0.1554	10.6904	10.4262

Framework versions

• Transformers 5.8.1
• Pytorch 2.11.0+cu130
• Datasets 4.8.5
• Tokenizers 0.22.2