CoolFace
Modelpublic

Nereboss/WhisperTiny20hCommonVoice10hAugment

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. -->

WhisperTiny20hCommonVoice10hAugment

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: 0.8526
  • —Wer: 0.4173

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
0.88670.44445001.03540.4892
0.77940.888910000.95360.4646
0.60751.333315000.90550.4392
0.58131.777820000.89040.4338
0.45982.222225000.87240.4262
0.43652.666730000.86470.4259
0.38133.111135000.85680.4188
0.38423.555640000.86050.4251
0.37354.045000.85600.4221
0.34114.444450000.85260.4173

Framework versions

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