CoolFace
Modelpublic

SmartWhatt/rangsitra-whisper-sm-selected-rgss-0.5-beta-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: 7.0732
  • —Wer: 23.6575
  • —Loss: 0.2032

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: 1013
  • —num_epochs: 5
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepCerWerValidation Loss
0.24731.020289.709233.53890.2188
0.15592.040568.619827.76830.1897
0.07723.060848.420027.07540.1928
0.02244.081127.401724.31600.1980
0.00465.0101407.073223.65750.2032

Framework versions

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