CoolFace
Modelpublic

Nereboss/WhisperTiny15hCommonVoice5hAugmentV2

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. -->

WhisperTiny15hCommonVoice5hAugmentV2

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: 0.9025
  • —Wer: 0.4359

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
0.80540.66935000.98660.4886
0.58221.338710000.91790.4688
0.49912.008015000.88080.4333
0.38642.677420000.88460.4295
0.26763.346725000.87380.4407
0.25984.016130000.87890.4324
0.18934.685435000.88290.4276
0.15145.354840000.90060.4256
0.14516.024145000.90210.4345
0.1376.693450000.90250.4359

Framework versions

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