whisper-medium-gabriel_fold_1

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: 0.2852
• Wer: 15.3917

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
0.7658	1.0	169	0.3021	14.4355
0.1396	2.0	338	0.2658	13.8186
0.0566	3.0	507	0.2666	14.0037
0.0252	4.0	676	0.2820	18.3837
0.0118	5.0	845	0.2801	13.6336
0.0067	6.0	1014	0.2852	15.3917

Framework versions

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