deepdml/whisper-small-ar-cv17

Whisper Small ar

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4878
• Wer: 59.8928

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: 64
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2097	1.6474	1000	0.3666	56.7025
0.0899	3.2949	2000	0.3687	61.4003
0.0516	4.9423	3000	0.3922	62.3124
0.0169	6.5898	4000	0.4581	58.6587
0.0072	8.2372	5000	0.4878	59.8928

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1