MarieGotthardt/whisper_tuned

Whisper Small sv-SE finetuned

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3758
• Wer: 27.8670

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• training_steps: 800

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6764	0.26	200	0.7241	45.5729
0.5502	0.52	400	0.5726	40.5878
0.4371	0.78	600	0.4403	31.7362
0.0905	1.03	800	0.3758	27.8670

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0