b-koopman's picture
Fix formatting
9e4c212
|
raw
history blame
1.39 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - PolyAI/minds14
model-index:
  - name: whisper-tiny-minds14-en
    results: []

whisper-tiny-minds14-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: 0.6170 Wer Ortho: 0.3880 Wer: 0.3512

  • eval_loss: 0.6170
  • eval_wer_ortho: 0.3880
  • eval_wer: 0.3512
  • eval_runtime: 22.3269
  • eval_samples_per_second: 5.061
  • eval_steps_per_second: 0.358
  • epoch: 8.93
  • step: 250

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

Framework versions

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