CoolFace
Modelpublic

SmartWhatt/rangsitra-whisper-sm-replace-0.5

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face
0likes4downloads
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. -->

Rangsitra Whisper

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • —Cer: 6.8869
  • —Wer: 23.6206
  • —Loss: 0.2097

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: 16
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: warmupstabledecay
  • —lrschedulerwarmup_steps: 1017
  • —num_epochs: 5
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepCerWerValidation Loss
0.16671.0203510.013533.99350.2194
0.10342.040709.230828.99930.1958
0.0613.061058.134826.56310.2008
0.02054.081407.152824.49290.2052
0.00595.0101756.886923.62060.2097

Framework versions

  • —Transformers 4.52.4
  • —Pytorch 2.9.1+cu128
  • —Datasets 3.6.0
  • —Tokenizers 0.21.4