whisper-ar-small-Version2

This model is a fine-tuned version of Moaaz5/whisper-ar-small-Data1 on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.8860
• eval_wer: 33.7509
• eval_runtime: 93.5042
• eval_samples_per_second: 0.898
• eval_steps_per_second: 0.118
• epoch: 21.0
• step: 441

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use 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: 200
• training_steps: 2000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3