metadata

license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_wermet_nosup_0015
    results: []

whisper_wermet_nosup_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:

Model description

More information needed

More information needed

More information needed

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

Train Loss	Train Accuracy	Train Wermet	Validation Loss	Validation Accuracy	Validation Wermet	Epoch
5.0860	0.0116	45.4352	4.4455	0.0124	36.1611	0
4.3098	0.0131	29.4890	4.0321	0.0144	24.9514	1
3.6711	0.0160	25.7380	2.7995	0.0205	32.2126	2
2.2582	0.0224	31.5946	1.6772	0.0257	23.9282	3
1.4268	0.0262	23.3380	1.2097	0.0279	18.7331	4
1.0613	0.0279	13.6764	0.9972	0.0289	10.7707	5
0.8545	0.0290	9.2746	0.8605	0.0296	6.5566	6
0.7144	0.0297	7.4723	0.7768	0.0300	5.4825	7
0.6116	0.0303	6.9092	0.7125	0.0304	6.5220	8
0.5307	0.0308	6.4113	0.6640	0.0306	5.7589	9
0.4647	0.0312	5.5865	0.6338	0.0309	4.8846	10
0.4085	0.0316	5.9874	0.6035	0.0310	3.8731	11
0.3602	0.0320	5.5558	0.5838	0.0311	6.3441	12
0.3184	0.0323	6.2887	0.5690	0.0312	3.9274	13
0.2807	0.0326	5.9455	0.5636	0.0313	5.3382	14