numan98/whisper-tiny-nextayah-v3

Nextayah Tiny Whisper Finetuned

This model is a fine-tuned version of tarteel-ai/whisper-tiny-ar-quran on the Synthetic Incorrect Verses dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1059
• eval_wer: 16.4345
• eval_runtime: 49.0992
• eval_samples_per_second: 2.037
• eval_steps_per_second: 0.265
• epoch: 68.9825
• step: 2000

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 750
• training_steps: 2500
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0