Baselhany/Whisper_tiny_fine_tune_Quran

Whisper tiny AR - BH

This model is a fine-tuned version of openai/whisper-tiny on the quran-ayat-speech-to-text dataset. It achieves the following results on the evaluation set:

• Loss: 0.0150
• Wer: 13.4379
• Cer: 4.1186

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 500
• num_epochs: 19
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Cer	Validation Loss	Wer
0.0258	0.1408	400	52.2218	0.0246	104.9348
0.0177	0.2817	800	10.2633	0.0184	26.2089
0.0116	0.4225	1200	7.3210	0.0160	20.9517
0.0101	0.5633	1600	5.8227	0.0141	17.5020
0.008	0.7042	2000	5.1235	0.0127	16.3695
0.0057	0.8450	2400	4.8168	0.0119	15.2343
0.0056	0.9858	2800	4.6678	0.0116	14.6364
0.0071	1.1267	3200	5.3042	0.0135	15.8929
0.0059	1.2676	3600	5.0437	0.0132	15.7165
0.0056	1.4084	4000	5.3648	0.0124	14.5758
0.0041	1.5492	4400	4.7531	0.0122	14.2259
0.0038	1.6901	4800	4.7431	0.0120	13.8043
0.004	1.8309	5200	4.9569	0.0119	14.1818
0.0036	1.9717	5600	4.9171	0.0118	14.0743
0.0033	2.1127	6000	5.0453	0.0129	15.0828
0.0033	2.2535	6400	5.1424	0.0128	14.9340
0.0033	2.3943	6800	5.0171	0.0123	14.7329
0.0033	2.5352	7200	4.3676	0.0122	13.6748
0.0034	2.6760	7600	4.5300	0.0122	13.5618
0.0025	2.8168	8000	4.4698	0.0122	13.3662
0.0028	2.9577	8400	4.5794	0.0122	13.5536
0.003	3.0986	8800	5.0764	0.0125	15.1021
0.0024	3.2394	9200	5.1331	0.0125	14.6943
0.0019	3.3802	9600	5.8448	0.0128	16.2924
0.0023	3.5211	10000	5.1642	0.0128	14.7301
0.002	3.6619	10400	4.9046	0.0127	13.8649
0.0018	3.8027	10800	4.9748	0.0126	13.6610
0.0021	3.9436	11200	5.0136	0.0126	13.8539
0.0018	4.0845	11600	5.0283	0.0132	14.6475
0.0018	4.2253	12000	4.5932	0.0132	13.7988
0.0022	4.3662	12400	4.3948	0.0130	13.7354
0.0025	4.5070	12800	4.7691	0.0131	14.3774
0.0018	4.6478	13200	4.8726	0.0131	14.0854
0.0016	4.7887	13600	4.7136	0.0130	14.0165
0.0018	4.9295	14000	4.7886	0.0130	14.0661
0.0017	5.0704	14400	4.5393	0.0133	14.0110
0.0013	5.2112	14800	4.3028	0.0132	13.7547
0.0017	5.3521	15200	4.5275	0.0133	14.2231
0.0014	5.4929	15600	4.6271	0.0135	14.1983
0.0016	5.6337	16000	4.3983	0.0134	13.8539
0.0015	5.7746	16400	4.2035	0.0134	13.5426
0.0016	5.9154	16800	4.2561	0.0134	13.6335
0.0015	6.0563	17200	4.3246	0.0134	13.6059
0.0015	6.1972	17600	4.1759	0.0137	13.6142
0.0016	6.3380	18000	4.2195	0.0137	13.5536
0.0014	6.4788	18400	4.4176	0.0137	13.8760
0.0015	6.6197	18800	4.2144	0.0137	13.5784
0.0015	6.7605	19200	4.1868	0.0137	13.4874
0.0016	6.9013	19600	4.0946	0.0137	13.3442
0.0015	7.0422	20000	4.1526	0.0139	13.5508
0.0012	7.1831	20400	4.1830	0.0139	13.5040
0.0011	7.3239	20800	4.0708	0.0138	13.3194
0.0017	7.4647	21200	4.0446	0.0138	13.3552
0.0012	7.6056	21600	4.0699	0.0139	13.3194
0.0011	7.7464	22000	4.0378	0.0140	13.3001
0.0012	7.8872	22400	4.0558	0.0139	13.3442
0.0012	8.0282	22800	4.1519	0.0140	13.6225
0.0011	8.1690	23200	4.1673	0.0142	13.4571
0.0013	8.3098	23600	4.1215	0.0141	13.5095
0.001	8.4507	24000	4.0753	0.0142	13.3827
0.0014	8.5915	24400	4.0683	0.0141	13.4985
0.0012	8.7323	24800	4.1103	0.0141	13.4985
0.0014	8.8732	25200	4.0273	0.0141	13.3579
0.0012	9.0141	25600	4.0276	0.0141	13.4075
0.0012	9.1549	26000	4.1824	0.0141	13.4379
0.0011	9.2957	26400	4.1019	0.0142	13.4268
0.0011	9.4366	26800	4.0923	0.0142	13.2946
0.001	9.5774	27200	4.0010	0.0143	13.2477
0.001	9.7182	27600	4.0398	0.0142	13.2560
0.0013	9.8591	28000	4.0109	0.0142	13.2560
0.001	9.9999	28400	4.0093	0.0142	13.2395
0.001	10.1408	28800	4.0721	0.0143	13.4020
0.0013	10.2817	29200	4.0817	0.0144	13.5536
0.0011	10.4225	29600	4.0897	0.0144	13.4902
0.0013	10.5633	30000	4.0567	0.0144	13.3414
0.0008	10.7042	30400	4.0587	0.0144	13.2973
0.0012	10.8450	30800	4.0724	0.0144	13.3249
0.0011	10.9858	31200	4.0590	0.0144	13.3028
0.0013	11.1267	31600	4.0023	0.0144	13.3001
0.0011	11.2676	32000	4.1324	0.0146	13.5894
0.0014	11.4084	32400	4.0923	0.0146	13.4627
0.0009	11.5492	32800	4.0414	0.0146	13.3827
0.0011	11.6901	33200	4.0436	0.0145	13.3717
0.0007	11.8309	33600	4.0622	0.0145	13.4103
0.0012	11.9717	34000	4.0491	0.0145	13.3910
0.001	12.1127	34400	4.1083	0.0145	13.5012
0.0009	12.2535	34800	4.0523	0.0146	13.3221
0.0011	12.3943	35200	4.1317	0.0146	13.4075
0.0009	12.5352	35600	4.0644	0.0147	13.3690
0.0009	12.6760	36000	4.1167	0.0147	13.4323
0.0011	12.8168	36400	4.1032	0.0147	13.4213
0.001	12.9577	36800	4.1064	0.0147	13.4323
0.001	13.0986	37200	4.1417	0.0147	13.5508
0.0012	13.2394	37600	4.1074	0.0147	13.3717
0.0011	13.3802	38000	4.0994	0.0148	13.3827
0.0009	13.5211	38400	4.0821	0.0147	13.4103
0.0012	13.6619	38800	4.0766	0.0148	13.3552
0.0009	13.8027	39200	4.0728	0.0148	13.3276
0.0011	13.9436	39600	4.0744	0.0148	13.3359
0.0007	14.0845	40000	4.0398	0.0147	13.3442
0.001	14.2253	40400	4.0641	0.0147	13.3607
0.001	14.3662	40800	4.1003	0.0148	13.3579
0.0011	14.5070	41200	4.1019	0.0148	13.4847
0.0009	14.6478	41600	4.1170	0.0148	13.4351
0.001	14.7887	42000	4.0750	0.0148	13.4020
0.0012	14.9295	42400	4.1173	0.0148	13.4434
0.0012	15.0704	42800	4.0917	0.0149	13.4985
0.0009	15.2112	43200	4.0958	0.0148	13.3607
0.001	15.3521	43600	4.0314	0.0148	13.3084
0.0009	15.4929	44000	4.0423	0.0148	13.3111
0.0008	15.6337	44400	4.0535	0.0148	13.3331
0.0007	15.7746	44800	4.0619	0.0148	13.3717
0.0009	15.9154	45200	4.0494	0.0148	13.3717
0.0008	16.0563	45600	4.1026	0.0149	13.3965
0.0007	16.1972	46000	4.0885	0.0148	13.3965
0.001	16.3380	46400	4.0712	0.0148	13.3745
0.0009	16.4788	46800	4.0673	0.0149	13.4103
0.0011	16.6197	47200	4.0699	0.0149	13.4654
0.001	16.7605	47600	4.0539	0.0149	13.3993
0.0007	16.9013	48000	4.0660	0.0149	13.3938
0.0012	17.0422	48400	4.0792	0.0149	13.4434
0.0009	17.1831	48800	4.0516	0.0149	13.3883
0.0008	17.3239	49200	4.0141	0.0150	13.3883
0.0011	17.4647	49600	4.0523	0.0149	13.3552
0.0006	17.6056	50000	4.0609	0.0149	13.3552
0.0009	17.7464	50400	4.0827	0.0149	13.4406
0.0007	17.8872	50800	4.0965	0.0149	13.4434
0.0011	18.0282	51200	0.0150	13.4020	4.0696
0.0007	18.1690	51600	0.0150	13.4516	4.0619
0.0008	18.3098	52000	0.0150	13.3276	4.0388
0.0009	18.4507	52400	0.0150	13.3414	4.0439
0.001	18.5915	52800	0.0150	13.4406	4.0930
0.0007	18.7323	53200	0.0150	13.4351	4.1163
0.0008	18.8732	53600	0.0150	13.4379	4.1186

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0