You can deploy this model and start earning money today!

smutuvi/
whisper-small-sw-common-voice-ndizi-782

Name: whisper-small-sw-common-voice-ndizi-782
Availability: InStock

peft

tensorboard

safetensors

generated_from_trainer

smutuvi/whisper-small-sw-common-voice

adapter

apache-2.0

Views

No views yet

whisper-small-sw-common-voice-ndizi-782

This model is a fine-tuned version of smutuvi/whisper-small-sw-common-voice on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.9420

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 100
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.0393	1.0	51	2.5562
1.9426	2.0	102	2.4939
1.9615	3.0	153	2.4289
1.7863	4.0	204	2.3723
1.8188	5.0	255	2.3275
1.707	6.0	306	2.2926
1.8352	7.0	357	2.2644
1.6285	8.0	408	2.2394
1.6887	9.0	459	2.2177
1.6399	10.0	510	2.1987
1.6828	11.0	561	2.1825
1.5906	12.0	612	2.1671
1.6641	13.0	663	2.1534
1.6976	14.0	714	2.1405
1.4269	15.0	765	2.1295
1.4999	16.0	816	2.1192
1.5153	17.0	867	2.1091
1.5006	18.0	918	2.0997
1.5664	19.0	969	2.0915
1.4385	20.0	1020	2.0833
1.4577	21.0	1071	2.0754
1.3832	22.0	1122	2.0683
1.4214	23.0	1173	2.0608
1.3889	24.0	1224	2.0546
1.3982	25.0	1275	2.0480
1.4601	26.0	1326	2.0428
1.4422	27.0	1377	2.0364
1.3789	28.0	1428	2.0322
1.3603	29.0	1479	2.0266
1.5143	30.0	1530	2.0224
1.3834	31.0	1581	2.0186
1.338	32.0	1632	2.0134
1.2825	33.0	1683	2.0110
1.4324	34.0	1734	2.0066
1.3716	35.0	1785	2.0032
1.3713	36.0	1836	2.0000
1.419	37.0	1887	1.9971
1.3179	38.0	1938	1.9940
1.3147	39.0	1989	1.9914
1.4404	40.0	2040	1.9887
1.2711	41.0	2091	1.9869
1.2966	42.0	2142	1.9835
1.2696	43.0	2193	1.9814
1.3286	44.0	2244	1.9790
1.271	45.0	2295	1.9766
1.2839	46.0	2346	1.9746
1.3299	47.0	2397	1.9734
1.2858	48.0	2448	1.9711
1.2222	49.0	2499	1.9697
1.3	50.0	2550	1.9684
1.305	51.0	2601	1.9664
1.3894	52.0	2652	1.9644
1.2221	53.0	2703	1.9635
1.2858	54.0	2754	1.9632
1.2739	55.0	2805	1.9615
1.1671	56.0	2856	1.9606
1.1928	57.0	2907	1.9590
1.2995	58.0	2958	1.9576
1.2287	59.0	3009	1.9572
1.191	60.0	3060	1.9559
1.2061	61.0	3111	1.9551
1.1362	62.0	3162	1.9546
1.155	63.0	3213	1.9537
1.2597	64.0	3264	1.9528
1.267	65.0	3315	1.9519
1.1355	66.0	3366	1.9503
1.2612	67.0	3417	1.9500
1.2262	68.0	3468	1.9494
1.2408	69.0	3519	1.9484
1.2042	70.0	3570	1.9481
1.1686	71.0	3621	1.9479
1.2891	72.0	3672	1.9474
1.3271	73.0	3723	1.9471
1.3009	74.0	3774	1.9464
1.1288	75.0	3825	1.9460
1.2342	76.0	3876	1.9456
1.2581	77.0	3927	1.9450
1.0447	78.0	3978	1.9448
1.2492	79.0	4029	1.9449
1.2316	80.0	4080	1.9443
1.0901	81.0	4131	1.9442
1.1115	82.0	4182	1.9444
1.1942	83.0	4233	1.9435
1.1974	84.0	4284	1.9434
1.2287	85.0	4335	1.9431
1.1252	86.0	4386	1.9429
1.0746	87.0	4437	1.9431
1.1975	88.0	4488	1.9432
1.2231	89.0	4539	1.9426
1.1957	90.0	4590	1.9426
1.1388	91.0	4641	1.9428
1.198	92.0	4692	1.9426
1.1479	93.0	4743	1.9423
1.1635	94.0	4794	1.9423
1.1184	95.0	4845	1.9422
1.1971	96.0	4896	1.9421
1.1907	97.0	4947	1.9418
1.0373	98.0	4998	1.9419
1.1927	99.0	5049	1.9421
1.1475	100.0	5100	1.9420

Framework versions

PEFT 0.7.2.dev0
Transformers 4.37.1
Pytorch 2.2.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0

smutuvi/whisper-small-sw-common-voice-ndizi-782

whisper-small-sw-common-voice-ndizi-782

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

smutuvi/
whisper-small-sw-common-voice-ndizi-782