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: 109
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.322	0.2986	109	0.5722	26.5302
0.421	0.5973	218	0.5081	23.2661
0.3857	0.8959	327	0.4898	21.8892
0.3523	1.1945	436	0.4843	21.9360
0.3301	1.4932	545	0.4772	21.4864
0.3187	1.7918	654	0.4686	21.2336
0.328	2.0904	763	0.4704	20.9713
0.2973	2.3890	872	0.4684	20.6201
0.2979	2.6877	981	0.4659	20.5264
0.2836	2.9863	1090	0.4646	20.6950

greenw0lf/whisper-new-nnat-20h-maxcos-ecapa

whisper-new-nnat-20h-maxcos-ecapa