verbalex-ar

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

• Loss: 0.0880
• Wer: 3.4815

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0015	5.2356	1000	0.0809	3.6620
0.0002	10.4712	2000	0.0845	3.5073
0.0001	15.7068	3000	0.0865	3.5245
0.0001	20.9424	4000	0.0877	3.5073
0.0001	26.1780	5000	0.0880	3.4815

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.2
• Datasets 2.16.0
• Tokenizers 0.19.1