whisper-medium-ft-1000_2

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: 0.3892
• Wer: 14.2726

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
1.4357	1.0	63	0.4359	29.4199
0.1744	2.0	126	0.3807	16.5746
0.057	3.0	189	0.3800	15.7919
0.0187	4.0	252	0.3829	14.4107
0.0068	5.0	315	0.3823	14.6409
0.0026	6.0	378	0.3892	14.2726

Framework versions

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