VoiceMath-Tiny-Tres

This model is a fine-tuned version of openai/whisper-tiny.en on the model_eng dataset. It achieves the following results on the evaluation set:

• Loss: 0.6083
• Wer: 10.0232

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:

• learning_rate: 1e-05
• train_batch_size: 8
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	100	0.4361	10.6729
No log	2.0	200	0.4749	10.1160
No log	3.0	300	0.4844	14.8956
No log	4.0	400	0.5087	10.3944
0.1884	5.0	500	0.5732	9.7912
0.1884	6.0	600	0.5863	9.9768
0.1884	7.0	700	0.5934	9.9768
0.1884	8.0	800	0.6067	10.0232
0.1884	9.0	900	0.6051	10.1160
0.001	10.0	1000	0.6083	10.0232

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3