metadata

library_name: transformers
language:
  - ar
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - automatic-speech-recognition
  - arabic
  - generated_from_trainer
datasets:
  - itskavya/gp
metrics:
  - wer
model-index:
  - name: Whisper Medium Informal Arabic
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Informal Arabic
          type: itskavya/gp
          config: default
          split: None
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 27.51652854083248

Whisper Medium Informal Arabic

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

Loss: 0.5486
Wer: 27.5165

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: 500
training_steps: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0515	4.0650	1000	0.4619	30.4498
0.0028	8.1301	2000	0.5296	28.2894
0.0005	12.1951	3000	0.5486	27.5165

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0