itskavya/whisper-small-informal-arabic-aug2

Whisper Small Informal Arabic

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

• Loss: 0.6089
• Wer: 36.1761
• Cer: 12.3818

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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.4019	5.2632	200	0.4761	37.1477	13.8042
0.0419	10.5263	400	0.5388	35.8882	12.1283
0.0055	15.7895	600	0.5828	35.5404	12.1001
0.0028	21.0526	800	0.6024	36.1641	12.4616
0.0022	26.3158	1000	0.6089	36.1761	12.3818

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1