README.md

metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - ylacombe/english_dialects
metrics:
  - wer
model-index:
  - name: Whisper Small Dv - khaled lakhdher
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ylacombe/english_dialects
          type: ylacombe/english_dialects
        metrics:
          - name: Wer
            type: wer
            value: 6.0064935064935066

Whisper Small Dv - khaled lakhdher

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

• Loss: 0.2430
• Wer Ortho: 6.5898
• Wer: 6.0065

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: 16
• 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: 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
0.0002	19.2308	500	0.2430	6.5898	6.0065

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0