Edit model card

whisper-tiny-finetuned-PolyAI-minds14

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: 0.5406
  • Wer Ortho: 0.3365
  • Wer: 0.3320

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: cosine
  • lr_scheduler_warmup_steps: 50
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
1.7677 1.79 50 0.7819 0.3903 0.3540
0.316 3.57 100 0.5342 0.3412 0.3379
0.1445 5.36 150 0.5394 0.3506 0.3469
0.1059 7.14 200 0.5406 0.3365 0.3320

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.0
  • Tokenizers 0.13.3
Downloads last month
7

Finetuned from

Dataset used to train weiren119/whisper-tiny-finetuned-PolyAI-minds14

Evaluation results