learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.4609	1.0316	500	1.1205	132.1684
0.9694	2.0632	1000	0.7589	100.8175
0.4373	4.0264	1500	0.2443	90.7214
0.2336	5.058	2000	0.2078	84.0997
0.1689	7.0212	2500	0.1942	79.9714
0.1322	8.0528	3000	0.1992	79.7466
0.1063	10.016	3500	0.2044	80.4210
0.0892	11.0476	4000	0.2040	78.7247
0.0755	13.0108	4500	0.2106	79.9918
0.0672	14.0424	5000	0.2092	79.8896

kavyamanohar/whisper-tiny-ml

whisper-tiny-ml