learning_rate: 3e-06
train_batch_size: 32
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Use OptimizerNames.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: 100
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
4.0799	1.2675	100	0.9942	98.0852	57.6877
2.3123	2.5350	200	0.5893	82.0259	34.1115
1.7020	3.8025	300	0.4698	78.3817	30.2375
1.1852	5.0637	400	0.3643	74.1198	28.8589
0.8702	6.3312	500	0.3100	72.9463	28.0338
0.7497	7.5987	600	0.3049	71.8962	27.2188
0.6472	8.8662	700	0.3017	71.9580	26.9873

Turiya33333/whisper-small-bengali-15DB-3e6

whisper-small-bengali-15DB-3e6