CoolFace
Modelpublic

yoona-J/ASR_Whisper_Disease_General

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes12downloads
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. -->

ASRWhisperDisease_General

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

  • —Loss: 0.1755
  • —Cer: 24.2276
  • —Wer: 29.8574

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: 3e-05
  • —trainbatchsize: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 339
  • —training_steps: 6780
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossCerWer
0.30180.442310000.322267.947269.5226
0.23780.884620000.246031.918342.8595
0.12071.326830000.217734.832837.2898
0.12881.769140000.192326.985033.9050
0.04382.211450000.185028.413334.9564
0.03752.653760000.175524.227629.8574

Framework versions

  • —Transformers 4.53.0.dev0
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.6.0
  • —Tokenizers 0.21.1