whisper-norwegian-tuned2

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5168
• Wer: 23.7738

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3886	1.0	298	0.4462	23.1580
0.2115	2.0	596	0.4398	22.6682
0.1478	3.0	894	0.4462	21.9188
0.0675	4.0	1192	0.4876	24.1226
0.0319	4.9849	1485	0.5168	23.7738

Framework versions

• Transformers 4.48.0
• Pytorch 2.8.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.4