whisper-base-khmer-v2

This model is a fine-tuned version of Vira21/Whisper-Base-KhmerV2 on the fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.2003
• Wer: 0.6096

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1065	0.3171	50	0.2027	0.6121
0.0973	0.6342	100	0.2014	0.6138
0.0933	0.9512	150	0.2003	0.6096
0.0816	1.2727	200	0.2020	0.6125
0.0767	1.5898	250	0.2025	0.6131
0.0782	1.9069	300	0.2027	0.6096
0.0728	2.2283	350	0.2044	0.6097
0.0692	2.5454	400	0.2043	0.6131
0.0685	2.8625	450	0.2043	0.6125

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0