whisper-medium-gabriel_fold_8

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: 0.2675
• Wer: 10.3753

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
0.6979	1.0	169	0.2737	13.6100
0.118	2.0	338	0.2458	11.4739
0.0437	3.0	507	0.2457	10.9246
0.0163	4.0	676	0.2616	12.0537
0.005	5.0	845	0.2628	10.5890
0.0016	6.0	1014	0.2675	10.3753

Framework versions

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