Edit model card

train_from_raw_cv12_true_suppress__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: 0.1762
  • Train Accuracy: 0.1054
  • Train Wermet: 4.0727
  • Validation Loss: 0.2885
  • Validation Accuracy: 0.0636
  • Validation Wermet: 9.9926
  • 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': 2e-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
2.3569 0.0439 2.6429 1.7869 0.0339 10.1374 0
1.7502 0.0561 3.2762 1.6607 0.0360 9.6159 1
1.6268 0.0595 3.0493 1.5698 0.0374 8.6767 2
1.5533 0.0614 2.3917 1.4965 0.0387 7.2278 3
1.4953 0.0631 1.8208 1.4549 0.0397 4.4667 4
1.4388 0.0647 1.7488 1.3669 0.0411 6.2695 5
1.3532 0.0670 1.6950 1.2392 0.0438 7.1167 6
1.2122 0.0710 1.6785 1.0705 0.0471 4.7509 7
1.0193 0.0768 1.8537 0.9080 0.0502 5.7317 8
0.8466 0.0823 2.3126 0.7098 0.0543 5.7454 9
0.7039 0.0870 2.3440 0.5934 0.0567 6.9383 10
0.5754 0.0914 2.3564 0.5071 0.0586 6.6276 11
0.4749 0.0949 2.6925 0.4391 0.0601 6.8169 12
0.3910 0.0978 3.0462 0.3908 0.0612 8.1284 13
0.3311 0.0999 3.3402 0.3658 0.0617 8.6094 14
0.2871 0.1015 3.4893 0.3344 0.0624 9.6494 15
0.2515 0.1027 3.6567 0.3234 0.0627 9.4059 16
0.2233 0.1037 3.8196 0.3058 0.0631 9.6761 17
0.1980 0.1046 3.9329 0.2916 0.0634 9.8163 18
0.1762 0.1054 4.0727 0.2885 0.0636 9.9926 19

Framework versions

  • Transformers 4.33.0.dev0
  • TensorFlow 2.13.0
  • Tokenizers 0.13.3
Downloads last month
5

Finetuned from