nocturneFlow/whisper-small-fleurs-kk

Whisper Small KK - Kazakh - Fleurs

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

• Loss: 0.3279
• Wer: 22.9994

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
0.0209	5.0	1000	0.2788	25.3670
0.001	10.0	2000	0.3062	23.1753
0.0004	15.0	3000	0.3216	22.9588
0.0003	20.0	4000	0.3279	22.9994

Framework versions

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