metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_input_decoder_shift_r_labels_no_force__0015
    results: []

whisper_input_decoder_shift_r_labels_no_force__0015

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: 3.3069
Train Accuracy: 0.0148
Train Wermet: 0.6961
Validation Loss: 3.1102
Validation Accuracy: 0.0124
Validation Wermet: 0.7609
Epoch: 14

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
5.6348	0.0091	1.5865	4.2935	0.0093	0.9579	0
4.9212	0.0099	0.9054	4.1262	0.0097	0.9390	1
4.6819	0.0107	0.8319	3.9071	0.0103	0.8966	2
4.4443	0.0114	0.8310	3.7367	0.0106	0.8939	3
4.2479	0.0119	0.8226	3.6101	0.0109	0.8696	4
4.0911	0.0124	0.8103	3.5364	0.0110	0.8946	5
3.9590	0.0127	0.7913	3.4556	0.0113	0.8388	6
3.8513	0.0130	0.7794	3.4106	0.0114	0.8515	7
3.7607	0.0133	0.7657	3.3507	0.0115	0.8261	8
3.6757	0.0136	0.7548	3.3141	0.0116	0.8400	9
3.6023	0.0138	0.7454	3.2711	0.0117	0.8006	10
3.5261	0.0140	0.7348	3.2391	0.0119	0.8101	11
3.4534	0.0143	0.7212	3.2070	0.0120	0.7870	12
3.3814	0.0146	0.7080	3.1505	0.0122	0.7826	13
3.3069	0.0148	0.6961	3.1102	0.0124	0.7609	14

Framework versions

Transformers 4.34.0.dev0
TensorFlow 2.13.0
Tokenizers 0.13.3