learning_rate: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.5
num_epochs: 16
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
4.3003	1.0	251	1.8420	77.7937	47.7279
2.9936	2.0	502	1.2434	77.3639	47.9117
2.8135	3.0	753	1.1431	74.9284	47.7279
2.4032	4.0	1004	1.0400	74.6418	47.1237
1.9765	5.0	1255	0.9656	74.2120	47.2551
1.8144	6.0	1506	0.8685	107.3066	74.4944
1.4479	7.0	1757	0.8158	63.8968	42.3431
1.2718	8.0	2008	0.7787	67.1920	45.3901
1.135	9.0	2259	0.7262	111.1748	98.4502
0.833	10.0	2510	0.7015	94.4126	61.3869
0.7509	11.0	2761	0.6963	62.1777	41.7914
0.7171	12.0	3012	0.6650	61.8911	42.9997
0.4706	13.0	3263	0.6258	77.6504	57.8671
0.4988	14.0	3514	0.6249	59.5989	40.5306
0.4503	15.0	3765	0.6201	59.1691	40.0841
0.3741	16.0	4016	0.6278	57.4499	38.7444

miosipof/asr2_medium_v0.3

Whisper Medium