whisper_input_decoder_shift_r_labels_no_force__0095

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: 0.0009
• Train Accuracy: 0.0340
• Train Wermet: 23.9254
• Validation Loss: 0.7893
• Validation Accuracy: 0.0211
• Validation Wermet: 25.1096
• Epoch: 94

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
5.6348	0.0091	1.5865	4.2935	0.0093	0.9579	0
4.9212	0.0099	0.9054	4.1262	0.0097	0.9390	1
4.6819	0.0107	0.8319	3.9071	0.0103	0.8966	2
4.4443	0.0114	0.8310	3.7367	0.0106	0.8939	3
4.2479	0.0119	0.8226	3.6101	0.0109	0.8696	4
4.0911	0.0124	0.8103	3.5364	0.0110	0.8946	5
3.9590	0.0127	0.7913	3.4556	0.0113	0.8388	6
3.8513	0.0130	0.7794	3.4106	0.0114	0.8515	7
3.7607	0.0133	0.7657	3.3507	0.0115	0.8261	8
3.6757	0.0136	0.7548	3.3141	0.0116	0.8400	9
3.6023	0.0138	0.7454	3.2711	0.0117	0.8006	10
3.5261	0.0140	0.7348	3.2391	0.0119	0.8101	11
3.4534	0.0143	0.7212	3.2070	0.0120	0.7870	12
3.3814	0.0146	0.7080	3.1505	0.0122	0.7826	13
3.3069	0.0148	0.6961	3.1102	0.0124	0.7609	14
3.2229	0.0152	0.6781	3.0542	0.0125	0.7532	15
3.1334	0.0156	0.6614	2.9840	0.0127	0.7448	16
3.0313	0.0160	0.6425	2.9032	0.0130	0.7123	17
2.9122	0.0166	0.6202	2.7986	0.0134	0.6930	18
2.7559	0.0173	0.5940	2.6337	0.0139	0.6673	19
2.5649	0.0182	0.5674	2.4490	0.0145	0.6383	20
2.3414	0.0193	0.5299	2.2785	0.0150	0.6183	21
2.0966	0.0206	0.4903	2.0460	0.0158	0.5649	22
1.8283	0.0220	0.4459	1.8369	0.0165	0.5306	23
1.5547	0.0235	0.3996	1.6356	0.0172	0.4848	24
1.3218	0.0249	0.3581	1.4682	0.0179	0.4510	25
1.1383	0.0260	0.3211	1.3465	0.0183	0.4226	26
0.9876	0.0270	0.2920	1.2323	0.0188	0.3966	27
0.8635	0.0278	0.2651	1.1482	0.0191	0.3749	28
0.7620	0.0284	0.2435	1.0816	0.0194	0.3565	29
0.6749	0.0290	0.2234	1.0187	0.0196	0.3433	30
0.5998	0.0295	0.2025	0.9761	0.0198	0.3319	31
0.5325	0.0300	0.1827	0.9326	0.0200	0.3213	32
0.4735	0.0305	0.1665	0.8942	0.0201	0.3110	33
0.4228	0.0308	0.1466	0.8735	0.0202	0.3026	34
0.3747	0.0312	0.1293	0.8408	0.0203	0.2931	35
0.3331	0.0316	0.1111	0.8253	0.0204	0.2891	36
0.2947	0.0319	0.0962	0.8084	0.0205	0.2849	37
0.2601	0.0322	0.0817	0.7906	0.0205	0.2783	38
0.2291	0.0324	0.0706	0.7876	0.0206	0.2755	39
0.2009	0.0327	0.0596	0.7723	0.0207	0.2712	40
0.1750	0.0329	0.0504	0.7629	0.0207	0.2692	41
0.1510	0.0331	0.0410	0.7650	0.0207	0.2684	42
0.1319	0.0333	0.0367	0.7533	0.0207	0.2655	43
0.1121	0.0335	0.0292	0.7589	0.0207	0.2647	44
0.0956	0.0336	0.0253	0.7579	0.0208	0.2642	45
0.0812	0.0337	0.0254	0.7584	0.0208	0.2625	46
0.0694	0.0338	0.0332	0.7555	0.0208	0.2693	47
0.0592	0.0339	0.0319	0.7534	0.0208	0.2629	48
0.0499	0.0339	0.0487	0.7587	0.0208	0.3030	49
0.0409	0.0339	0.0615	0.7577	0.0208	0.2810	50
0.0347	0.0340	0.0859	0.7603	0.0208	0.3534	51
0.0286	0.0340	0.1928	0.7554	0.0209	0.5822	52
0.0267	0.0340	0.3131	0.7664	0.0208	1.7372	53
0.0243	0.0340	1.3154	0.7525	0.0209	0.7770	54
0.0206	0.0340	0.8121	0.7532	0.0209	0.9253	55
0.0174	0.0340	0.9253	0.7574	0.0209	1.4865	56
0.0135	0.0340	1.1761	0.7592	0.0209	1.5813	57
0.0111	0.0340	1.7125	0.7631	0.0209	1.8950	58
0.0096	0.0340	1.9230	0.7664	0.0209	2.4432	59
0.0082	0.0340	2.5718	0.7693	0.0209	3.3565	60
0.0073	0.0340	3.5489	0.7747	0.0209	3.7191	61
0.0063	0.0340	3.7801	0.7756	0.0209	4.4728	62
0.0054	0.0340	4.0145	0.7795	0.0209	5.0058	63
0.0048	0.0340	4.9652	0.7821	0.0210	4.9937	64
0.0042	0.0340	5.5984	0.7914	0.0209	8.3869	65
0.0205	0.0339	9.9212	0.7811	0.0209	21.1156	66
0.0184	0.0339	8.3175	0.7619	0.0210	0.5360	67
0.0080	0.0340	0.6373	0.7554	0.0211	0.4090	68
0.0052	0.0340	0.5550	0.7528	0.0211	0.3938	69
0.0038	0.0340	0.4678	0.7551	0.0211	0.7911	70
0.0032	0.0340	1.1632	0.7617	0.0211	0.5495	71
0.0028	0.0340	0.7869	0.7643	0.0211	1.4089	72
0.0025	0.0340	1.5997	0.7681	0.0211	1.1413	73
0.0023	0.0340	1.7042	0.7719	0.0211	1.7576	74
0.0021	0.0340	2.3363	0.7750	0.0211	2.2434	75
0.0019	0.0340	2.9550	0.7777	0.0211	2.3071	76
0.0017	0.0340	3.1713	0.7831	0.0211	3.3338	77
0.0015	0.0340	3.9077	0.7852	0.0211	3.6442	78
0.0014	0.0340	4.3375	0.7900	0.0211	4.0113	79
0.0013	0.0340	4.9777	0.7946	0.0211	5.1689	80
0.0011	0.0340	5.9846	0.7968	0.0211	5.6006	81
0.0010	0.0340	6.6595	0.8033	0.0211	6.1998	82
0.0009	0.0340	7.3520	0.8058	0.0211	7.6034	83
0.0008	0.0340	8.1210	0.8138	0.0211	7.8284	84
0.0007	0.0340	8.9352	0.8170	0.0211	9.1346	85
0.0006	0.0340	10.2307	0.8185	0.0211	10.8739	86
0.0006	0.0340	12.2734	0.8245	0.0211	12.5682	87
0.0005	0.0340	13.1276	0.8314	0.0211	14.4535	88
0.0124	0.0339	14.3527	0.8265	0.0209	32.3895	89
0.0144	0.0339	13.6342	0.7995	0.0211	10.7092	90
0.0045	0.0340	23.6659	0.7859	0.0211	46.8917	91
0.0019	0.0340	23.3120	0.7861	0.0211	34.2423	92
0.0013	0.0340	25.9218	0.7861	0.0212	31.2443	93
0.0009	0.0340	23.9254	0.7893	0.0211	25.1096	94

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3