whisper-medium-nn-v3

This model is a fine-tuned version of openai/whisper-medium on the Stortingskorpuset dataset. It achieves the following results on the evaluation set:

• Loss: 0.2116
• Wer: 11.3376

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• training_steps: 8000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4413	0.25	2000	0.4447	26.7707
0.1945	1.1	4000	0.3042	17.8344
0.1013	1.35	6000	0.2421	14.2138
0.0308	2.2	8000	0.2116	11.3376

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu117
• Datasets 2.11.0
• Tokenizers 0.13.2