whisper-tiny-en-US / README.md
J3's picture
update model card README.md
36372a8
metadata
language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
metrics:
  - wer
model-index:
  - name: whisper tiny en-US - J3v2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: PolyAI/minds14-en-US
          type: PolyAI/minds14
          config: en-US
          split: train[450:]
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 0.33116883116883117

whisper tiny en-US - J3v2

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

  • Loss: 0.7183
  • Wer Ortho: 0.3381
  • Wer: 0.3312

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
0.0012 17.86 500 0.7183 0.3381 0.3312

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3