learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: 300
training_steps: 3000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
2.9271	0.0833	250	1.3054	68.7188
0.9135	0.1667	500	0.9644	60.0228
0.8868	0.25	750	0.8687	53.9910
0.9087	0.3333	1000	0.8401	49.2948
0.6559	1.0833	1250	0.8037	47.1363
0.5987	1.1667	1500	0.8014	48.5949
0.6388	1.25	1750	0.7862	47.0331
0.7091	1.3333	2000	0.7814	46.2495
0.519	2.0833	2250	0.7693	43.1472
0.5015	2.1667	2500	0.7675	47.3892
0.5478	2.25	2750	0.7626	45.8701
0.6383	2.3333	3000	0.7570	43.7277

wwwtwwwt/whisper-tiny-Lifestyle

whisper-tiny-Lifestyle