KrorngAI/whisper-small-finetuned-km-v2

Whisper Small Kh - Kimang Khun

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: 0.1502
• Wer: 39.3470

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.SGD and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0337	0.5587	100	0.1549	36.2614
0.0324	1.1173	200	0.1550	35.7258
0.0324	1.6760	300	0.1549	35.7793
0.0288	2.2346	400	0.1550	35.8329

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.2.0
• Tokenizers 0.22.1