CoolFace
Modelpublic

Nereboss/WhisperTiny30hCommonVoice0.0Augment

sourceHugging Faceapache-2.0updated 2y 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. -->

WhisperTiny30hCommonVoice0.0Augment

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: 0.8173
  • —Wer: 0.4007

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
0.73840.44055000.99080.4775
0.62750.881110000.89600.4447
0.49191.321615000.86040.4225
0.49131.762120000.84500.4177
0.36672.202625000.82730.4090
0.34622.643230000.83620.4095
0.32393.083735000.81990.4061
0.31693.524240000.82020.4023
0.31233.964845000.81120.3996
0.29514.405350000.81730.4007

Framework versions

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