CoolFace
Modelpublic

Nereboss/WhisperTiny22.5hCommonVoice7.5hAugment

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. -->

WhisperTiny22.5hCommonVoice7.5hAugment

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: 0.8516
  • —Wer: 0.4159

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
0.83350.44375001.02730.5001
0.71440.887310000.94200.4956
0.5821.331015000.90390.4563
0.55571.774620000.87430.4367
0.48232.218325000.87230.4329
0.43652.661930000.85760.4279
0.38053.105635000.85810.4205
0.37663.549240000.85190.4253
0.3683.992945000.85070.4171
0.33734.436650000.85160.4159

Framework versions

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