README.md

metadata

language:
  - ar
license: mit
base_model: distil-whisper/distil-large-v2
tags:
  - generated_from_trainer
datasets:
  - nadsoft/Jordan-Audio
metrics:
  - wer
model-index:
  - name: Hamsa distill alfa
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: nadsoft/Jordan-Audio
          type: nadsoft/Jordan-Audio
        metrics:
          - name: Wer
            type: wer
            value: 54.11225658648339

Hamsa distill alfa

This model is a fine-tuned version of distil-whisper/distil-large-v2 on the nadsoft/Jordan-Audio dataset. It achieves the following results on the evaluation set:

• Loss: 0.8474
• Wer Ortho: 56.1657
• Wer: 54.1123

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.7394	1.76	500	0.8474	56.1657	54.1123

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1