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: 91
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.6936	0.2984	91	0.6340	45.6095
0.3958	0.5967	182	0.5687	33.3396
0.3687	0.8951	273	0.5474	28.3426
0.3232	1.1934	364	0.5466	29.8319
0.2992	1.4918	455	0.5458	27.5371
0.3277	1.7902	546	0.5312	26.2352
0.3002	2.0885	637	0.5286	25.6357
0.2726	2.3869	728	0.5317	27.2655
0.2821	2.6852	819	0.5328	26.3991
0.2643	2.9836	910	0.5305	26.4319

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

whisper-new-nnat-10h-maxcos-ecapa