CoolFace
Modelpublic

kimbochen/whisper-small-zh-tw

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
4likes46downloads
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. -->

Whisper Small Traditional Chinese

This model is a fine-tuned version of kimbochen/whisper-small-zh-tw on the mozilla-foundation/commonvoice11_0 zh-TW dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4334
  • —Wer: 32.0420

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: 64
  • —evalbatchsize: 32
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 1200
  • —training_steps: 2000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.00662.054000.374332.9100
0.00845.038000.378733.4171
0.00988.0112000.397933.2481
0.001910.0616000.408432.3116
0.000813.0420000.433432.0420

Framework versions

  • —Transformers 4.26.0.dev0
  • —Pytorch 1.13.0+cu116
  • —Datasets 2.7.1.dev0
  • —Tokenizers 0.13.2