whisper-med-LoRA_r64_a64

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

• Loss: 0.3052
• Wer: 13.4913

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.8163	1.0	2801	0.4584	18.6509
0.3618	2.0	5602	0.3682	15.8800
0.305	3.0	8403	0.3289	14.2748
0.2769	4.0	11204	0.3099	13.6633
0.2626	5.0	14005	0.3052	13.4913

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3