CoolFace
Modelpublic

shg1421/whisper-small-decoder

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes5downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Whisper

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

  • —Loss: 0.3409
  • —Wer: 10.5283

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
  • —trainbatchsize: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.03054.5510000.247111.1359
0.01179.0920000.316810.3795
0.002413.6430000.331210.4291
0.000618.1840000.340910.5283

Framework versions

  • —Transformers 4.39.0.dev0
  • —Pytorch 1.12.1+cu102
  • —Datasets 2.15.0
  • —Tokenizers 0.15.0