whisper_input_decoder_no_lob__0035

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: 1.2828
• Train Accuracy: 0.0254
• Train Wermet: 0.3431
• Validation Loss: 1.3555
• Validation Accuracy: 0.0192
• Validation Wermet: 0.4097
• Epoch: 34

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
5.4122	0.0107	0.9328	3.9759	0.0114	0.9606	0
4.7176	0.0116	0.8683	3.9404	0.0114	0.9334	1
4.6750	0.0117	0.8478	3.9211	0.0115	0.9237	2
4.6511	0.0117	0.8413	3.8864	0.0115	0.9331	3
4.6294	0.0118	0.8270	3.8729	0.0115	0.9228	4
4.6134	0.0118	0.8199	3.8690	0.0114	0.9451	5
4.5980	0.0118	0.8102	3.8491	0.0115	0.9152	6
4.5759	0.0119	0.7890	3.8366	0.0116	0.8691	7
4.5518	0.0120	0.7694	3.8081	0.0116	0.9013	8
4.5219	0.0121	0.7591	3.7734	0.0118	0.8383	9
4.4761	0.0122	0.7400	3.7156	0.0120	0.8125	10
4.4139	0.0125	0.7257	3.6311	0.0121	0.8188	11
4.3113	0.0128	0.7127	3.5089	0.0124	0.8008	12
4.1608	0.0132	0.7088	3.3587	0.0127	0.7742	13
3.9595	0.0138	0.7012	3.1493	0.0132	0.7718	14
3.7188	0.0145	0.6820	2.8784	0.0139	0.7292	15
3.4775	0.0153	0.6678	2.6716	0.0144	0.7074	16
3.2575	0.0160	0.6481	2.4980	0.0149	0.6764	17
3.0615	0.0167	0.6314	2.3456	0.0153	0.6476	18
2.8715	0.0174	0.6094	2.2090	0.0158	0.6210	19
2.6930	0.0181	0.5931	2.0918	0.0162	0.5992	20
2.5383	0.0187	0.5739	1.9769	0.0166	0.5791	21
2.3952	0.0193	0.5512	1.9042	0.0168	0.5589	22
2.2427	0.0201	0.5333	1.8028	0.0172	0.5394	23
2.1236	0.0206	0.5174	1.7434	0.0174	0.5240	24
2.0315	0.0211	0.4978	1.6755	0.0177	0.5084	25
1.9066	0.0217	0.4773	1.6534	0.0178	0.4947	26
1.8279	0.0221	0.4596	1.5606	0.0182	0.4788	27
1.7325	0.0227	0.4412	1.5173	0.0184	0.4667	28
1.6416	0.0232	0.4199	1.4733	0.0186	0.4511	29
1.5702	0.0236	0.4028	1.4519	0.0187	0.4442	30
1.4787	0.0241	0.3839	1.4213	0.0188	0.4322	31
1.4238	0.0244	0.3700	1.3971	0.0190	0.4272	32
1.3561	0.0249	0.3594	1.3499	0.0192	0.4171	33
1.2828	0.0254	0.3431	1.3555	0.0192	0.4097	34

Framework versions

• Transformers 4.33.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3