whisper-medium-arabic

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

Whisper Medium Arabic

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

• eval_loss: 0.0794
• eval_wer: 5.4226
• eval_runtime: 200.1714
• eval_samples_per_second: 0.5
• eval_steps_per_second: 0.5
• epoch: 5.7143
• step: 250

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 400

Framework versions

• Transformers 4.41.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1