CoolFace
Modelpublic

Nereboss/WhisperTiny15hCommonVoice15hAugment

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes3downloads
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. -->

WhisperTiny15hCommonVoice15hAugment

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: 0.8652
  • —Wer: 0.4183

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
0.94920.44645001.03680.4824
0.77590.892910000.93550.4505
0.60861.339315000.89930.4374
0.56361.785720000.88550.4282
0.43432.232125000.87260.4342
0.42282.678630000.87140.4204
0.35853.12535000.85910.4194
0.33023.571440000.86740.4179
0.32354.017945000.86400.4186
0.30324.464350000.86520.4183

Framework versions

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