whisper-medium-el / README.md
emilios's picture
Update README.md (#2)
bae2b76
metadata
language:
  - el
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
  - hf-asr-leaderboard
datasets:
  - mozilla-foundation/common_voice_11_0
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Medium El Greco Greek
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          args: 'config: el, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 13.976597325408619

Whisper Medium El - Greek One

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4707
  • Wer: 13.9766

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: 20
  • 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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0036 10.01 1000 0.4461 15.9082
0.0001 20.02 2000 0.4250 14.5245
0.0 31.0 3000 0.4526 14.1902
0.0 41.01 4000 0.4657 14.1252
0.0 52.0 5000 0.4707 13.9766

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2