whisper_4_with_init_sun_syl_wd_0__0045

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: 0.8201
• Train Accuracy: 0.0288
• Train Wermet: 0.2114
• Train Wermet Syl: 0.2108
• Validation Loss: 1.2056
• Validation Accuracy: 0.0201
• Validation Wermet: 0.3601
• Validation Wermet Syl: 0.3270
• Epoch: 44

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}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Wermet	Train Wermet Syl	Validation Loss	Validation Accuracy	Validation Wermet	Validation Wermet Syl	Epoch
5.3409	0.0111	1.3547	1.2898	3.9789	0.0114	0.9710	0.9563	0
4.7143	0.0116	0.8622	0.8228	3.9404	0.0113	0.9823	0.9735	1
4.6752	0.0117	0.8472	0.8057	3.9081	0.0114	0.9579	0.9359	2
4.6500	0.0117	0.8382	0.7945	3.8820	0.0115	0.9213	0.8856	3
4.6282	0.0118	0.8286	0.7805	3.8738	0.0114	0.9433	0.9119	4
4.6095	0.0118	0.8190	0.7696	3.8630	0.0115	0.9117	0.8698	5
4.5875	0.0119	0.7976	0.7465	3.8341	0.0116	0.8976	0.8552	6
4.5682	0.0120	0.7753	0.7227	3.8277	0.0116	0.9014	0.8653	7
4.5376	0.0121	0.7528	0.7005	3.7844	0.0118	0.8332	0.7815	8
4.5060	0.0122	0.7392	0.6844	3.7537	0.0118	0.8578	0.8152	9
4.4580	0.0124	0.7221	0.6694	3.7038	0.0120	0.8190	0.7679	10
4.3989	0.0125	0.7156	0.6636	3.6169	0.0122	0.7979	0.7429	11
4.3056	0.0128	0.7069	0.6557	3.5098	0.0125	0.7924	0.7396	12
4.1673	0.0132	0.7054	0.6584	3.3542	0.0128	0.7759	0.7240	13
3.9762	0.0138	0.6987	0.6559	3.1318	0.0133	0.7644	0.7231	14
3.7385	0.0145	0.6835	0.6448	2.9144	0.0138	0.7392	0.6955	15
3.5040	0.0152	0.6644	0.6298	2.7413	0.0142	0.7019	0.6548	16
3.2728	0.0160	0.6408	0.6101	2.5183	0.0149	0.6798	0.6363	17
3.0657	0.0167	0.6188	0.5912	2.3594	0.0153	0.6528	0.6103	18
2.8703	0.0174	0.5936	0.5685	2.2644	0.0156	0.6310	0.5925	19
2.6850	0.0181	0.5680	0.5453	2.1296	0.0160	0.6040	0.5652	20
2.5227	0.0188	0.5423	0.5215	2.0019	0.0165	0.5793	0.5403	21
2.3878	0.0194	0.5199	0.5015	1.8996	0.0169	0.5592	0.5229	22
2.2437	0.0201	0.4959	0.4788	1.8141	0.0172	0.5414	0.5045	23
2.1205	0.0207	0.4752	0.4607	1.7245	0.0175	0.5208	0.4838	24
1.9919	0.0213	0.4533	0.4390	1.6673	0.0178	0.5026	0.4659	25
1.9140	0.0217	0.4355	0.4216	1.6041	0.0181	0.4873	0.4512	26
1.8225	0.0222	0.4184	0.4052	1.6271	0.0179	0.4852	0.4511	27
1.7265	0.0227	0.4016	0.3895	1.5219	0.0184	0.4635	0.4275	28
1.6240	0.0233	0.3833	0.3729	1.4718	0.0186	0.4515	0.4170	29
1.5610	0.0236	0.3697	0.3588	1.4404	0.0188	0.4407	0.4056	30
1.4719	0.0242	0.3540	0.3449	1.4125	0.0189	0.4310	0.3961	31
1.4152	0.0245	0.3421	0.3339	1.3655	0.0191	0.4234	0.3881	32
1.3546	0.0249	0.3277	0.3195	1.3419	0.0192	0.4156	0.3816	33
1.2565	0.0256	0.3135	0.3060	1.3172	0.0194	0.4065	0.3722	34
1.2135	0.0258	0.3026	0.2958	1.3019	0.0194	0.4006	0.3662	35
1.1739	0.0261	0.2923	0.2861	1.3843	0.0190	0.3951	0.3587	36
1.0950	0.0267	0.2782	0.2733	1.2665	0.0197	0.3883	0.3541	37
1.0435	0.0271	0.2673	0.2631	1.2567	0.0197	0.3837	0.3497	38
0.9922	0.0275	0.2580	0.2542	1.2566	0.0197	0.3801	0.3444	39
0.9387	0.0279	0.2464	0.2438	1.2441	0.0198	0.3767	0.3423	40
0.9345	0.0278	0.2393	0.2373	1.2221	0.0199	0.3682	0.3336	41
0.8574	0.0285	0.2268	0.2255	1.2258	0.0199	0.3680	0.3338	42
0.8275	0.0287	0.2183	0.2180	1.2044	0.0201	0.3628	0.3290	43
0.8201	0.0288	0.2114	0.2108	1.2056	0.0201	0.3601	0.3270	44

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3