whisper-medium-gabriel_fold_7

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: 0.2762
• Wer: 10.4733

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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6954	1.0	169	0.2696	12.4580
0.1179	2.0	338	0.2583	12.1832
0.0424	3.0	507	0.2713	11.6641
0.0159	4.0	676	0.2692	11.2366
0.0054	5.0	845	0.2720	10.5038
0.0022	6.0	1014	0.2762	10.4733

Framework versions

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