nocturneFlow/whisper-small-common-kk

Whisper Small Kk - Kazakh

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6964
• Wer: 46.1466

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0018	15.1515	1000	0.6017	49.5578
0.0002	30.3030	2000	0.6563	46.5572
0.0001	45.4545	3000	0.6854	46.1150
0.0001	60.6061	4000	0.6964	46.1466

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu118
• Datasets 3.3.2
• Tokenizers 0.21.0