whisper_input_decoder_no_lob__0005

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: 4.6294
• Train Accuracy: 0.0118
• Train Wermet: 0.8270
• Validation Loss: 3.8729
• Validation Accuracy: 0.0115
• Validation Wermet: 0.9228
• Epoch: 4

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

Framework versions

• Transformers 4.33.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3