alexstokes/whisper-small-eg

Whisper Small - Egyptian Arabic

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

• Loss: 0.9560
• Wer: 41.6677

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0518	7.6336	1000	0.7113	42.9166
0.004	15.2672	2000	0.8712	41.2157
0.001	22.9008	3000	0.9327	42.0245
0.0006	30.5344	4000	0.9560	41.6677

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.1.post303
• Datasets 3.1.0
• Tokenizers 0.20.3