CoolFace
Modelpublic

sujithvemi/whisper-medium-physician-dictation-gpt-4-turbo

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
1likes7downloads
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 Large v3 Physician Dictation GPT 4 turbo

This model is a fine-tuned version of openai/whisper-medium on the Physician Dictation GPT 4 Turbo dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.1660
  • —Wer: 5.3497

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: 8
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —training_steps: 8500
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.01433.96835000.10684.9948
0.00237.936510000.12875.0757
0.002611.904815000.12544.9409
0.000315.873020000.12984.7298
0.00119.841325000.13125.0173
0.000123.809530000.14055.2374
0.000127.777835000.14544.9903
0.000131.746040000.14975.2104
0.035.714345000.15315.1835
0.039.682550000.15585.1431
0.043.650855000.15815.1296
0.047.619060000.16015.1700
0.051.587365000.16195.1925
0.055.555670000.16355.2329
0.059.523875000.16485.2733
0.063.492180000.16565.3362
0.067.460385000.16605.3497

Framework versions

  • —Transformers 4.40.2
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1