README.md

metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - MohamedRashad/arabic-english-code-switching
metrics:
  - wer
model-index:
  - name: whisper-small-arabic
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: arabic-english-code-switching
          type: MohamedRashad/arabic-english-code-switching
        metrics:
          - name: Wer
            type: wer
            value: 46.235411803934646

whisper-small-arabic

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

• Loss: 0.7021
• Wer: 46.2354

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5366	1.6026	1000	0.7021	46.2354

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1