whisper-medium-gabriel_fold_9

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: 0.2576
• Wer: 10.4403

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
0.7003	1.0	169	0.2413	12.1069
0.1182	2.0	338	0.2245	11.5723
0.0448	3.0	507	0.2239	24.3082
0.0147	4.0	676	0.2437	10.1887
0.0042	5.0	845	0.2497	10.0943
0.0016	6.0	1014	0.2576	10.4403

Framework versions

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