augm-model

This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0402
• Wer: 5.6716

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1068	0.43	200	0.0819	16.8370
0.0997	0.86	400	0.0617	13.6318
0.0595	1.29	600	0.0528	7.7769
0.0609	1.72	800	0.0444	6.9437
0.0375	2.15	1000	0.0402	5.6716

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2