whisper_char_cv12_pad_lob100_low__0005 – AI Model by bigmorning | AlphaNeural AI

You can deploy this model and start earning money today!

bigmorning/
whisper_char_cv12_pad_lob100_low__0005

like

0

automatic-speech-recognition

generated_from_keras_callback

openai/whisper-tiny

endpoints_compatible

Views

No views yet

whisper_char_cv12_pad_lob100_low__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: 0.2488
Train Accuracy: 0.1028
Train Wermet: 2.3286
Validation Loss: 0.3305
Validation Accuracy: 0.0626
Validation Wermet: 9.1756
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
0.3330	0.0999	1.7359	0.3779	0.0615	4.7471	0
0.3093	0.1007	2.0563	0.3652	0.0618	7.2181	1
0.2869	0.1015	2.0654	0.3539	0.0620	8.6857	2
0.2672	0.1022	2.1925	0.3443	0.0623	8.0906	3
0.2488	0.1028	2.3286	0.3305	0.0626	9.1756	4

Framework versions

Transformers 4.33.0.dev0
TensorFlow 2.13.0
Tokenizers 0.13.3