whisper-small-ar / README.md
atishay23's picture
Upload tokenizer
9dfdd1f verified
metadata
language:
  - ar
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - arab
metrics:
  - wer
base_model: openai/whisper-small
model-index:
  - name: Whisper Small ar - Atishay Sharma
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: arabic
          type: arab
          config: default
          split: train
          args: 'config: ar, split: test'
        metrics:
          - type: wer
            value: 4.545454545454546
            name: Wer

Whisper Small ar - Atishay Sharma

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

  • Loss: 0.0922
  • Wer: 4.5455

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: 8
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0 500.0 500 0.0922 4.5455

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2