CoolFace
Modelpublic

xbilek25/wme_30s_Static_atWall_1.7

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes2downloads
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. -->

wme30sStaticatWall1.7

This model is a fine-tuned version of openai/whisper-medium.en on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.9489
  • —Wer: 26.5156

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: 48
  • —evalbatchsize: 32
  • —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: 60
  • —training_steps: 528
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
No log001.514834.2009
0.56460.1667880.981829.8224
0.4311.00191760.947630.8328
0.17361.16862640.930227.1280
0.13642.00383520.945327.4342
0.05052.17054400.938327.6791
0.04723.00575280.948926.5156

Framework versions

  • —Transformers 4.51.3
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.6.0
  • —Tokenizers 0.21.1