CoolFace
Modelpublic

Nereboss/WhisperTiny15hCommonVoice45hAugment

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes1downloads
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. -->

WhisperTiny15hCommonVoice45hAugment

This model is a fine-tuned version of OpenAI/whisper-tiny on the audiofolder dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.8665
  • —Wer: 0.4280

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: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 5000

Training results

Training LossEpochStepValidation LossWer
1.02580.22335001.05450.4943
0.88280.446610000.97980.4687
0.80230.669915000.93880.4608
0.7140.893320000.91100.4420
0.59271.116625000.89400.4363
0.59741.339930000.88720.4352
0.54591.563235000.87640.4319
0.52451.786540000.87650.4279
0.53252.009845000.87090.4280
0.4792.233150000.86650.4280

Framework versions

  • —Transformers 4.48.3
  • —Pytorch 2.6.0
  • —Datasets 3.3.0
  • —Tokenizers 0.21.0