pashto-voice-modal

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5049
• Wer: 0.2812

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4989	3.3333	500	0.4834	0.4674
0.0944	6.6667	1000	0.5559	0.4611
0.0166	10.0	1500	0.6398	0.4512
0.6217	1.2797	2000	0.4274	0.4084
0.5870	1.5997	2500	0.3868	0.3689
0.5616	1.9197	3000	0.3637	0.3480
0.3566	2.2394	3500	0.3656	0.3371
0.3577	2.5594	4000	0.3569	0.3353
0.3836	2.8794	4500	0.3460	0.3294
0.2361	3.1990	5000	0.3615	0.3264
0.2615	3.5190	5500	0.3611	0.3269
0.2261	3.8390	6000	0.3613	0.3163
0.1367	4.1587	6500	0.3863	0.3313
0.1311	4.4787	7000	0.3953	0.3196
0.1461	4.7987	7500	0.3938	0.3207
0.0687	5.1184	8000	0.4159	0.3188
0.0712	5.4384	8500	0.4247	0.3218
0.0637	5.7584	9000	0.4341	0.3270
0.0272	6.0781	9500	0.4626	0.3214
0.0265	6.3981	10000	0.4743	0.3249
0.0286	6.7181	10500	0.4840	0.3283
0.0130	7.0378	11000	0.5048	0.3252
0.0140	7.3578	11500	0.5258	0.3232
0.0149	7.6778	12000	0.5335	0.3239
0.0099	7.9978	12500	0.5436	0.3253
0.0060	8.3174	13000	0.5647	0.3247
0.0042	8.6374	13500	0.5766	0.3242
0.0036	8.9574	14000	0.5812	0.3237
0.0030	9.2771	14500	0.5961	0.3236
0.0020	9.5971	15000	0.6007	0.3228
0.0028	9.9171	15500	0.6031	0.3232
0.0033	10.0	15630	0.6031	0.3234
0.4836	3.4130	16000	0.3362	0.3104
0.4733	3.5197	16500	0.3174	0.2981
0.4600	3.6263	17000	0.3087	0.2934
0.4260	3.7330	17500	0.3039	0.2962
0.4497	3.8397	18000	0.3068	0.2860
0.4544	3.9463	18500	0.3034	0.2890
0.3037	4.0529	19000	0.3307	0.2944
0.3195	4.1596	19500	0.3085	0.2896
0.3188	4.2662	20000	0.3086	0.2956
0.3393	4.3729	20500	0.3076	0.2902
0.3102	4.4796	21000	0.3159	0.3010
0.3551	4.5862	21500	0.3042	0.2914
0.3262	4.6929	22000	0.3005	0.2812
0.3344	4.7996	22500	0.3042	0.2770
0.3467	4.9062	23000	0.2999	0.2842
0.2083	5.0128	23500	0.3277	0.2890
0.2006	5.1195	24000	0.3301	0.2908
0.2152	5.2261	24500	0.3312	0.2812
0.1919	5.3328	25000	0.3334	0.2830
0.2288	5.4395	25500	0.3238	0.2902
0.3328	5.5461	26000	0.3275	0.2806
0.2134	5.6528	26500	0.3351	0.2842
0.2369	5.7595	27000	0.3278	0.2770
0.2402	5.8661	27500	0.3217	0.2734
0.2235	5.9728	28000	0.3288	0.2794
0.1639	6.0794	28500	0.3608	0.2806
0.1453	6.1860	29000	0.3719	0.2842
0.1315	6.2927	29500	0.3655	0.2848
0.1306	6.3994	30000	0.3641	0.2914
0.1362	6.5060	30500	0.3600	0.2806
0.2540	6.6127	31000	0.3643	0.2794
0.1496	6.7194	31500	0.3740	0.2854
0.1373	6.8260	32000	0.3656	0.2854
0.1249	6.9327	32500	0.3711	0.2854
0.0881	7.0393	33000	0.3879	0.2890
0.0772	7.1459	33500	0.3944	0.2866
0.0568	7.2526	34000	0.4016	0.2866
0.0833	7.3593	34500	0.4104	0.2734
0.0753	7.4659	35000	0.4060	0.2860
0.0707	7.5726	35500	0.4122	0.2884
0.0784	7.6793	36000	0.4119	0.2848
0.0943	7.7859	36500	0.4103	0.2836
0.0957	7.8926	37000	0.4177	0.2872
0.1002	7.9993	37500	0.4147	0.2854
0.1211	8.1058	38000	0.4517	0.2914
0.0498	8.2125	38500	0.4490	0.2896
0.0423	8.3191	39000	0.4532	0.2836
0.0553	8.4258	39500	0.4589	0.2818
0.0403	8.5325	40000	0.4667	0.2848
0.0576	8.6391	40500	0.4577	0.2860
0.0558	8.7458	41000	0.4601	0.2758
0.0562	8.8525	41500	0.4696	0.2776
0.0416	8.9591	42000	0.4671	0.2794
0.0297	9.0657	42500	0.4862	0.2848
0.0439	9.1724	43000	0.4896	0.2818
0.0173	9.2790	43500	0.4967	0.2836
0.0320	9.3857	44000	0.4978	0.2848
0.0325	9.4924	44500	0.5011	0.2824
0.0278	9.5990	45000	0.4998	0.2800
0.0302	9.7057	45500	0.5014	0.2770
0.0340	9.8124	46000	0.5035	0.2776
0.0371	9.9190	46500	0.5028	0.2788
0.0380	10.0	46880	0.5049	0.2812

Framework versions

• Transformers 5.5.4
• Pytorch 2.6.0+cu124
• Datasets 4.8.4
• Tokenizers 0.22.2