whisper-small-ha-lora

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: 0.2139
• Wer: 17.6735

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
0.2851	0.0756	200	0.2240	18.1992
0.2844	0.1512	400	0.2199	18.3235
0.2849	0.2268	600	0.2166	17.9602
0.2842	0.3025	800	0.2161	17.6353
0.2631	0.3781	1000	0.2139	17.6735

Framework versions

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