learning_rate: 0.0001
train_batch_size: 48
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch_fused 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: 59
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.4332	0.2995	59	0.6828	31.1806
0.4937	0.5990	118	0.5383	23.9873
0.3968	0.8985	177	0.5136	23.0366
0.402	1.1980	236	0.5016	22.7369
0.3518	1.4975	295	0.4921	21.8517
0.3556	1.7970	354	0.4859	22.0344
0.3345	2.0964	413	0.4839	21.9313
0.3128	2.3959	472	0.4810	21.9220
0.3074	2.6954	531	0.4791	21.7253
0.3198	2.9949	590	0.4781	21.6925

greenw0lf/whisper-new-nnat-10h-caps-ecapa

whisper-new-nnat-10h-caps-ecapa