learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.1042	50	1.9269	32.1898
No log	0.2083	100	1.4797	43.1861
No log	0.3125	150	1.2178	40.5545
No log	0.4167	200	1.0703	29.6053
No log	0.5208	250	0.8933	29.3233
No log	0.625	300	0.7411	28.8064
No log	0.7292	350	0.6687	28.3835
No log	0.8333	400	0.6253	27.7256
No log	0.9375	450	0.5987	27.6786
1.1123	1.0417	500	0.5814	27.4906
1.1123	1.1458	550	0.5713	27.0207
1.1123	1.25	600	0.5637	26.5508
1.1123	1.3542	650	0.5575	25.7049
1.1123	1.4583	700	0.5536	25.4229
1.1123	1.5625	750	0.5505	25.2820
1.1123	1.6667	800	0.5480	25.4699
1.1123	1.7708	850	0.5460	25.4229
1.1123	1.875	900	0.5441	25.5639
1.1123	1.9792	950	0.5432	25.7049
0.5954	2.0833	1000	0.5414	25.6109
0.5954	2.1875	1050	0.5403	25.5639
0.5954	2.2917	1100	0.5384	25.6109
0.5954	2.3958	1150	0.5378	25.3759
0.5954	2.5	1200	0.5374	25.3289
0.5954	2.6042	1250	0.5360	25.0940
0.5954	2.7083	1300	0.5352	25.1880
0.5954	2.8125	1350	0.5346	25.1880
0.5954	2.9167	1400	0.5337	25.0470
0.5954	3.0208	1450	0.5336	25.2350
0.5723	3.125	1500	0.5334	25.7989
0.5723	3.2292	1550	0.5323	25.2350
0.5723	3.3333	1600	0.5323	25.1880
0.5723	3.4375	1650	0.5317	24.8590
0.5723	3.5417	1700	0.5315	25.2350
0.5723	3.6458	1750	0.5305	25.3289
0.5723	3.75	1800	0.5297	25.0940
0.5723	3.8542	1850	0.5295	25.1410
0.5723	3.9583	1900	0.5293	25.0470
0.5723	4.0625	1950	0.5284	25.0470
0.5663	4.1667	2000	0.5281	24.9530
0.5663	4.2708	2050	0.5280	25.0
0.5663	4.375	2100	0.5279	24.8590
0.5663	4.4792	2150	0.5280	24.9060
0.5663	4.5833	2200	0.5276	25.0940
0.5663	4.6875	2250	0.5274	24.9530
0.5663	4.7917	2300	0.5262	24.9060
0.5663	4.8958	2350	0.5259	24.9060
0.5663	5.0	2400	0.5265	25.0

rishithabcdefghijklmnop/whisper_large_v2_indian_accent

whisper_large_v2_indian_accent