whisper-med-LoRA_nosie_128_64_45k

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: 0.2688
• Wer: 11.7434

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7607	1.0	2863	0.3811	15.2075
0.3282	2.0	5726	0.3135	13.0948
0.2741	3.0	8589	0.2881	12.0860
0.2476	4.0	11452	0.2744	11.8196
0.2339	5.0	14315	0.2688	11.7434

Framework versions

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