You can deploy this model and start earning money today!

smutuvi/
whisper-small-sw-common-voice-ndizi-158

Name: whisper-small-sw-common-voice-ndizi-158
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-158

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: 1.8656

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
No log	1.0	18	1.7772
0.0199	2.0	36	1.7806
0.0215	3.0	54	1.7789
0.0215	4.0	72	1.7854
0.0182	5.0	90	1.7913
0.0188	6.0	108	1.7917
0.0174	7.0	126	1.7891
0.0174	8.0	144	1.7907
0.0187	9.0	162	1.7929
0.016	10.0	180	1.7960
0.016	11.0	198	1.8023
0.0159	12.0	216	1.8095
0.0179	13.0	234	1.8001
0.0143	14.0	252	1.8097
0.0143	15.0	270	1.8057
0.0158	16.0	288	1.8053
0.0152	17.0	306	1.8090
0.0152	18.0	324	1.8058
0.0143	19.0	342	1.8105
0.0143	20.0	360	1.8126
0.0145	21.0	378	1.8156
0.0145	22.0	396	1.8117
0.0144	23.0	414	1.8158
0.0142	24.0	432	1.8168
0.0135	25.0	450	1.8166
0.0135	26.0	468	1.8187
0.0143	27.0	486	1.8209
0.0122	28.0	504	1.8232
0.0122	29.0	522	1.8211
0.014	30.0	540	1.8240
0.011	31.0	558	1.8281
0.0124	32.0	576	1.8264
0.0124	33.0	594	1.8237
0.0134	34.0	612	1.8262
0.0124	35.0	630	1.8336
0.0124	36.0	648	1.8297
0.0127	37.0	666	1.8293
0.0117	38.0	684	1.8313
0.012	39.0	702	1.8288
0.012	40.0	720	1.8344
0.0106	41.0	738	1.8334
0.0125	42.0	756	1.8388
0.0125	43.0	774	1.8421
0.0112	44.0	792	1.8344
0.0111	45.0	810	1.8369
0.0105	46.0	828	1.8443
0.0105	47.0	846	1.8379
0.0112	48.0	864	1.8443
0.0109	49.0	882	1.8378
0.0116	50.0	900	1.8423
0.0116	51.0	918	1.8407
0.0109	52.0	936	1.8418
0.0099	53.0	954	1.8443
0.0099	54.0	972	1.8463
0.0107	55.0	990	1.8456
0.0105	56.0	1008	1.8458
0.01	57.0	1026	1.8507
0.01	58.0	1044	1.8472
0.01	59.0	1062	1.8477
0.0101	60.0	1080	1.8481
0.0101	61.0	1098	1.8551
0.0106	62.0	1116	1.8498
0.0107	63.0	1134	1.8514
0.0092	64.0	1152	1.8476
0.0092	65.0	1170	1.8568
0.0104	66.0	1188	1.8561
0.0099	67.0	1206	1.8560
0.0099	68.0	1224	1.8509
0.0093	69.0	1242	1.8540
0.01	70.0	1260	1.8483
0.01	71.0	1278	1.8557
0.01	72.0	1296	1.8574
0.0091	73.0	1314	1.8584
0.0097	74.0	1332	1.8594
0.0091	75.0	1350	1.8556
0.0091	76.0	1368	1.8524
0.0103	77.0	1386	1.8551
0.0086	78.0	1404	1.8549
0.0086	79.0	1422	1.8586
0.0102	80.0	1440	1.8603
0.0081	81.0	1458	1.8562
0.0096	82.0	1476	1.8611
0.0096	83.0	1494	1.8579
0.0095	84.0	1512	1.8624
0.0087	85.0	1530	1.8561
0.0087	86.0	1548	1.8557
0.0092	87.0	1566	1.8610
0.0087	88.0	1584	1.8574
0.0095	89.0	1602	1.8612
0.0095	90.0	1620	1.8623
0.0096	91.0	1638	1.8626
0.008	92.0	1656	1.8609
0.008	93.0	1674	1.8636
0.0088	94.0	1692	1.8659
0.0096	95.0	1710	1.8655
0.0091	96.0	1728	1.8608
0.0091	97.0	1746	1.8632
0.0088	98.0	1764	1.8616
0.0091	99.0	1782	1.8662
0.0088	100.0	1800	1.8656

Framework versions

PEFT 0.7.2.dev0
Transformers 4.37.0.dev0
Pytorch 2.0.0
Datasets 2.16.1
Tokenizers 0.15.0

smutuvi/whisper-small-sw-common-voice-ndizi-158

whisper-small-sw-common-voice-ndizi-158

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

smutuvi/
whisper-small-sw-common-voice-ndizi-158