whisper_4_with_init_sun__0065

This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.4037
• Train Accuracy: 0.0324
• Train Wermet: 0.0912
• Validation Loss: 1.1798
• Validation Accuracy: 0.0206
• Validation Wermet: 0.3272
• Epoch: 64

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Wermet	Validation Loss	Validation Accuracy	Validation Wermet	Epoch
5.3333	0.0111	1.3132	3.9675	0.0114	0.9339	0
4.7131	0.0116	0.8607	3.9360	0.0114	0.9503	1
4.6717	0.0117	0.8449	3.9196	0.0113	0.9768	2
4.6474	0.0117	0.8338	3.9039	0.0114	0.9557	3
4.6273	0.0118	0.8243	3.8721	0.0115	0.9414	4
4.6101	0.0118	0.8167	3.8629	0.0116	0.9156	5
4.5912	0.0119	0.7985	3.8361	0.0116	0.8988	6
4.5645	0.0120	0.7753	3.8298	0.0116	0.9045	7
4.5386	0.0121	0.7558	3.7904	0.0118	0.8426	8
4.5075	0.0122	0.7405	3.7472	0.0119	0.8103	9
4.4586	0.0124	0.7255	3.7163	0.0120	0.8189	10
4.3978	0.0126	0.7174	3.6168	0.0122	0.8163	11
4.3031	0.0128	0.7107	3.4956	0.0125	0.7847	12
4.1606	0.0133	0.7025	3.3414	0.0128	0.7897	13
3.9636	0.0138	0.6991	3.1311	0.0133	0.7495	14
3.7290	0.0145	0.6827	2.8892	0.0139	0.7292	15
3.4993	0.0152	0.6643	2.7195	0.0143	0.7129	16
3.2810	0.0159	0.6448	2.5418	0.0148	0.6803	17
3.0604	0.0167	0.6182	2.3572	0.0153	0.6538	18
2.8748	0.0174	0.5946	2.2575	0.0156	0.6337	19
2.6889	0.0181	0.5699	2.0988	0.0162	0.6016	20
2.5493	0.0187	0.5449	1.9878	0.0166	0.5834	21
2.3921	0.0194	0.5207	1.9029	0.0168	0.5597	22
2.2491	0.0201	0.4987	1.8642	0.0169	0.5409	23
2.1254	0.0207	0.4766	1.7354	0.0175	0.5231	24
1.9980	0.0213	0.4552	1.6661	0.0178	0.5049	25
1.9147	0.0217	0.4382	1.6140	0.0180	0.4921	26
1.8008	0.0223	0.4196	1.5652	0.0182	0.4742	27
1.7185	0.0228	0.4028	1.5159	0.0184	0.4632	28
1.6401	0.0232	0.3867	1.4891	0.0185	0.4548	29
1.5786	0.0235	0.3728	1.5141	0.0183	0.4548	30
1.4950	0.0241	0.3582	1.4345	0.0188	0.4340	31
1.4323	0.0244	0.3448	1.3694	0.0191	0.4226	32
1.3495	0.0250	0.3319	1.3780	0.0190	0.4172	33
1.3007	0.0253	0.3187	1.3296	0.0193	0.4109	34
1.2320	0.0257	0.3074	1.3116	0.0194	0.4029	35
1.1836	0.0261	0.2958	1.3025	0.0195	0.3992	36
1.1131	0.0266	0.2842	1.2885	0.0195	0.3894	37
1.0630	0.0269	0.2730	1.2627	0.0197	0.3850	38
1.0189	0.0272	0.2628	1.2633	0.0197	0.3822	39
1.0025	0.0273	0.2550	1.2561	0.0197	0.3760	40
0.9498	0.0277	0.2445	1.2288	0.0199	0.3710	41
0.9027	0.0281	0.2337	1.2188	0.0199	0.3684	42
0.8469	0.0286	0.2240	1.2072	0.0200	0.3637	43
0.8056	0.0289	0.2153	1.2046	0.0201	0.3599	44
0.7761	0.0291	0.2070	1.1989	0.0201	0.3579	45
0.7369	0.0295	0.1982	1.1938	0.0202	0.3528	46
0.7026	0.0298	0.1902	1.1934	0.0202	0.3508	47
0.6976	0.0298	0.1834	1.1803	0.0203	0.3469	48
0.6880	0.0298	0.1765	1.1844	0.0203	0.3470	49
0.6674	0.0300	0.1702	1.1741	0.0203	0.3446	50
0.6099	0.0305	0.1606	1.1753	0.0203	0.3440	51
0.5972	0.0306	0.1549	1.1692	0.0204	0.3401	52
0.5555	0.0310	0.1475	1.1744	0.0204	0.3382	53
0.5275	0.0313	0.1412	1.1743	0.0204	0.3384	54
0.5103	0.0315	0.1344	1.1720	0.0205	0.3355	55
0.5268	0.0313	0.1308	1.1709	0.0205	0.3343	56
0.5060	0.0315	0.1251	1.2090	0.0203	0.3318	57
0.4696	0.0318	0.1172	1.1748	0.0205	0.3321	58
0.4737	0.0318	0.1136	1.1764	0.0205	0.3313	59
0.4749	0.0318	0.1115	1.1684	0.0206	0.3289	60
0.4208	0.0323	0.1015	1.1704	0.0206	0.3275	61
0.3895	0.0326	0.0958	1.1777	0.0206	0.3286	62
0.3721	0.0328	0.0909	1.1754	0.0206	0.3267	63
0.4037	0.0324	0.0912	1.1798	0.0206	0.3272	64

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3