deepdml/whisper-small-ar-mix

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: 2.0345
• Wer: 60.9988

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
0.1333	0.2	1000	1.6477	58.9201
0.0766	1.0454	2000	1.8054	62.8257
0.0554	1.2454	3000	1.8952	55.9413
0.0358	2.0908	4000	1.9780	64.4329
0.0203	2.2908	5000	2.0345	60.9988

Framework versions

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