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: 63
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.9169	0.2972	63	0.7278	41.9660
0.3981	0.5943	126	0.6059	43.3522
0.3374	0.8915	189	0.5844	50.2318
0.2899	1.1887	252	0.5708	43.8440
0.2836	1.4858	315	0.5627	38.2195
0.3081	1.7830	378	0.5542	35.4283
0.2832	2.0802	441	0.5556	36.0184
0.2731	2.3774	504	0.5539	36.5101
0.2471	2.6745	567	0.5524	35.9341
0.2567	2.9717	630	0.5519	34.7398

greenw0lf/whisper-new-nnat-5h-maxcos-ecapa

whisper-new-nnat-5h-maxcos-ecapa