t3ngr1/whisper-small-kk

Whisper Small kk - t3ngr1

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8049
• Wer: 52.2628

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: 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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0014	20.0	1000	0.6866	52.0017
0.0002	40.0	2000	0.7461	51.3055
0.0001	60.0	3000	0.7767	52.3934
0.0001	80.0	4000	0.7969	52.1323
0.0	100.0	5000	0.8049	52.2628

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu118
• Datasets 3.6.0
• Tokenizers 0.21.1