whisper_charsplit_new_0020

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: 0.0463
• Train Accuracy: 0.0787
• Train Wermet: 11.9677
• Validation Loss: 0.3402
• Validation Accuracy: 0.0760
• Validation Wermet: 10.2814
• Epoch: 19

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
0.8733	0.0602	13.0686	0.6470	0.0676	11.4066	0
0.5740	0.0666	12.7778	0.5113	0.0706	11.1022	1
0.4553	0.0692	12.2404	0.4371	0.0723	10.9105	2
0.3813	0.0708	11.9157	0.3935	0.0733	9.4615	3
0.3292	0.0720	11.5732	0.3630	0.0740	9.9885	4
0.2886	0.0729	11.5171	0.3403	0.0745	9.8042	5
0.2561	0.0736	11.3173	0.3256	0.0749	9.9431	6
0.2282	0.0743	11.7308	0.3159	0.0752	9.2086	7
0.2036	0.0748	11.4503	0.3071	0.0754	9.5236	8
0.1820	0.0754	11.7175	0.3005	0.0756	10.0755	9
0.1628	0.0758	11.7056	0.2993	0.0757	9.9497	10
0.1450	0.0762	11.7637	0.2971	0.0758	10.1481	11
0.1287	0.0766	11.8509	0.3029	0.0759	10.2042	12
0.1140	0.0770	12.1100	0.3004	0.0760	10.3873	13
0.0998	0.0773	11.9502	0.3025	0.0761	10.7066	14
0.0872	0.0777	12.3196	0.3129	0.0759	10.7707	15
0.0760	0.0779	12.2637	0.3142	0.0761	10.2638	16
0.0651	0.0782	12.1215	0.3192	0.0761	10.0750	17
0.0547	0.0785	12.0551	0.3294	0.0761	10.4732	18
0.0463	0.0787	11.9677	0.3402	0.0760	10.2814	19

Framework versions

• Transformers 4.32.0.dev0
• TensorFlow 2.12.0
• Tokenizers 0.13.3