whisper-medium-gabriel_fold_6

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: 0.2775
• Wer: 10.3823

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
0.7001	1.0	169	0.2615	11.8744
0.1175	2.0	338	0.2532	11.4081
0.0423	3.0	507	0.2481	10.8486
0.0147	4.0	676	0.2615	10.8486
0.0042	5.0	845	0.2720	10.6310
0.0014	6.0	1014	0.2775	10.3823

Framework versions

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