whisper-tiny-dv

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2334
• Wer Ortho: 75.2207
• Wer: 21.4903

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: 4
• eval_batch_size: 4
• seed: 42
• 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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
1.0239	0.4078	500	1.0369	129.9576	87.4794
0.912	0.8157	1000	0.9221	100.7646	72.9711
0.6815	1.2235	1500	0.7174	99.4926	62.4261
0.2529	1.6313	2000	0.3188	87.6972	34.2327
0.1906	2.0392	2500	0.2608	80.2808	24.9043
0.1666	2.4470	3000	0.2457	76.8054	21.4851
0.1511	2.8548	3500	0.2271	75.5265	21.5943
0.117	3.2626	4000	0.2334	75.2207	21.4903

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 2.20.0
• Tokenizers 0.21.1