whisper_input_decoder_shift_r_labels_with_force__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: 0.1194
• Train Accuracy: 0.0334
• Train Wermet: 0.3137
• Validation Loss: 0.7596
• Validation Accuracy: 0.0207
• Validation Wermet: 0.5479
• 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': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Wermet	Validation Loss	Validation Accuracy	Validation Wermet	Epoch
5.6249	0.0091	1.7162	4.2965	0.0094	0.9447	0
4.9223	0.0099	0.9041	4.1562	0.0097	0.9327	1
4.6814	0.0107	0.8376	3.9245	0.0103	0.8927	2
4.4407	0.0114	0.8311	3.7252	0.0107	0.8775	3
4.2445	0.0119	0.8228	3.6283	0.0108	0.8695	4
4.0889	0.0123	0.8067	3.5310	0.0110	0.8916	5
3.9575	0.0127	0.7908	3.4478	0.0113	0.8407	6
3.8547	0.0130	0.7781	3.4227	0.0113	0.8670	7
3.7599	0.0133	0.7654	3.3519	0.0115	0.8375	8
3.6763	0.0136	0.7543	3.3183	0.0116	0.8678	9
3.6006	0.0138	0.7421	3.2581	0.0117	0.8120	10
3.5300	0.0140	0.7296	3.2415	0.0118	0.8257	11
3.4554	0.0143	0.7179	3.2163	0.0119	0.8078	12
3.3930	0.0145	0.7057	3.1612	0.0121	0.7758	13
3.3218	0.0148	0.6946	3.1357	0.0122	0.7760	14
3.2424	0.0151	0.6806	3.0812	0.0123	0.7639	15
3.1577	0.0155	0.6633	3.0193	0.0126	0.7428	16
3.0655	0.0159	0.6454	2.9643	0.0128	0.7423	17
2.9579	0.0164	0.6271	2.8510	0.0132	0.7103	18
2.8149	0.0170	0.6022	2.7020	0.0136	0.6811	19
2.6475	0.0178	0.5775	2.5406	0.0142	0.6495	20
2.4340	0.0189	0.5451	2.3364	0.0149	0.6166	21
2.2002	0.0200	0.5065	2.1300	0.0155	0.5766	22
1.9511	0.0213	0.4658	1.9335	0.0162	0.5419	23
1.6777	0.0228	0.4184	1.7327	0.0169	0.5071	24
1.4282	0.0243	0.3754	1.5461	0.0176	0.4669	25
1.2219	0.0255	0.3365	1.4027	0.0181	0.4326	26
1.0535	0.0265	0.3016	1.2979	0.0185	0.4134	27
0.9205	0.0274	0.2731	1.1891	0.0189	0.3843	28
0.8079	0.0281	0.2453	1.1135	0.0192	0.3659	29
0.7140	0.0288	0.2218	1.0532	0.0195	0.3495	30
0.6318	0.0293	0.1975	0.9976	0.0197	0.3351	31
0.5623	0.0298	0.1770	0.9571	0.0199	0.3256	32
0.4990	0.0303	0.1582	0.9184	0.0200	0.3147	33
0.4444	0.0307	0.1424	0.8865	0.0202	0.3062	34
0.3949	0.0311	0.1260	0.8532	0.0203	0.2968	35
0.3505	0.0314	0.1118	0.8333	0.0204	0.2898	36
0.3104	0.0317	0.0988	0.8245	0.0204	0.2881	37
0.2743	0.0321	0.0886	0.8014	0.0205	0.2825	38
0.2428	0.0323	0.0842	0.7944	0.0206	0.2794	39
0.2120	0.0326	0.0880	0.7742	0.0206	0.2762	40
0.1863	0.0328	0.1289	0.7744	0.0206	0.2863	41
0.1621	0.0330	0.1792	0.7683	0.0207	0.2873	42
0.1390	0.0332	0.1918	0.7664	0.0207	0.4006	43
0.1194	0.0334	0.3137	0.7596	0.0207	0.5479	44

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3