whisper-tiny-en / README.md
Marco-Cheung's picture
End of training
465e931
metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
metrics:
  - wer
model-index:
  - name: whisper-tiny-en
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: PolyAI/minds14
          type: PolyAI/minds14
          config: en-US
          split: train[451:]
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 0.3500298151460942

whisper-tiny-en

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6528
  • Wer Ortho: 0.3529
  • Wer: 0.3500

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: 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

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.0011 17.24 500 0.6528 0.3529 0.3500

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.3
  • Tokenizers 0.13.3