whisper-medium-el / README.md
emilios's picture
update model card README.md
7f6c586
|
raw
history blame
2.19 kB
metadata
language:
  - el
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Medium El Greco
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: el
          split: test
          args: el
        metrics:
          - name: Wer
            type: wer
            value: 10.74479940564636

Whisper Medium El Greco

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: 0.4245
  • Wer: 10.7448

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: 32
  • eval_batch_size: 16
  • 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: 7000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0039 2.49 1000 0.3787 12.4443
0.0017 4.98 2000 0.4010 12.2864
0.0006 7.46 3000 0.4108 11.6921
0.0004 9.95 4000 0.4221 11.5806
0.0005 12.44 5000 0.4222 11.4134
0.0006 4.03 6000 0.4230 10.9212
0.0006 9.03 7000 0.4245 10.7448

Framework versions

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