whisper-small-ha-lora-v2

This model is a fine-tuned version of therealbee/whisper-small-ha-finetuned on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1832
• Wer: 15.2170

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 50
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2686	0.5242	200	0.1977	16.7368
0.2343	1.0472	400	0.1896	16.1059
0.2109	1.5714	600	0.1869	15.9816
0.1981	2.0944	800	0.1831	15.1118
0.1858	2.6186	1000	0.1832	15.2170

Framework versions

• PEFT 0.19.1
• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 5.0.0
• Tokenizers 0.22.2