whisper_new_split_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: 0.0899
• Train Accuracy: 0.0330
• Train Wermet: 24.8354
• Validation Loss: 0.4715
• Validation Accuracy: 0.0313
• Validation Wermet: 21.1618
• 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
5.1027	0.0113	52.5530	4.4267	0.0121	41.4796	0
4.3285	0.0126	38.6893	3.9835	0.0145	33.6050	1
3.4573	0.0168	30.7714	2.5568	0.0215	31.7559	2
2.0878	0.0226	20.5131	1.5738	0.0257	21.2159	3
1.3529	0.0258	17.4367	1.1712	0.0276	17.7695	4
0.9953	0.0275	18.7308	0.9389	0.0287	20.5259	5
0.7852	0.0286	18.5731	0.8074	0.0294	17.6576	6
0.6428	0.0293	18.2945	0.7219	0.0298	19.9850	7
0.5384	0.0299	18.9258	0.6610	0.0301	18.9327	8
0.4565	0.0304	19.0749	0.6117	0.0304	21.9796	9
0.3901	0.0308	19.2099	0.5693	0.0306	18.0965	10
0.3348	0.0312	20.4777	0.5449	0.0307	19.9518	11
0.2877	0.0315	20.3181	0.5232	0.0309	20.4017	12
0.2471	0.0318	19.2073	0.5057	0.0310	18.7612	13
0.2120	0.0320	19.0961	0.4925	0.0311	22.3187	14
0.1809	0.0323	20.7944	0.4849	0.0311	27.2314	15
0.1539	0.0325	22.0951	0.4787	0.0312	25.2171	16
0.1299	0.0327	22.7652	0.4733	0.0312	22.7492	17
0.1087	0.0329	25.2223	0.4701	0.0312	28.9044	18
0.0899	0.0330	24.8354	0.4715	0.0313	21.1618	19

Framework versions

• Transformers 4.27.0.dev0
• TensorFlow 2.11.0
• Tokenizers 0.13.2