whisper-med-LoRA_FAA_data_small

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: 4.4632
• Wer: 56.9444

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.4359	1.0	1	4.5014	56.9444
4.4359	2.0	2	4.5014	56.9444
4.4359	3.0	3	4.5496	56.9444
4.458	4.0	4	4.5496	56.9444
4.4576	5.0	5	4.5439	56.9444
4.4411	6.0	6	4.4745	56.9444
4.4139	7.0	7	4.4745	56.9444
4.4166	8.0	8	4.4745	56.9444
4.4181	9.0	9	4.4722	56.9444
4.379	10.0	10	4.4632	56.9444

Framework versions

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