CoolFace
Modelpublic

rlaorrn/working

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes6downloads
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. -->

jeju_stt

This model is a fine-tuned version of openai/whisper-base on the jeju_audio dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3821
  • —Cer: 11.9723

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossCer
0.36892.010000.385013.3992
0.18874.020000.348211.9225
0.10576.030000.360311.8446
0.06378.040000.382111.9723

Framework versions

  • —Transformers 4.42.0.dev0
  • —Pytorch 2.1.2
  • —Datasets 2.18.0
  • —Tokenizers 0.19.1