CoolFace
Modelpublic

p4b/limiwhisper-small-ko-dia-gs

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face
1likes11downloads
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 Ko(Gyungsang dialect) - p4b

This model is a fine-tuned version of openai/whisper-small on the KR Dialect Speech - gyungsang dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2017
  • —Wer: 15.9300

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: 5e-07
  • —trainbatchsize: 96
  • —evalbatchsize: 64
  • —seed: 42
  • —distributed_type: multi-GPU
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 5000

Training results

Training LossEpochStepValidation LossWer
0.59090.210000.4133211.6022
0.36120.420000.213716.9429
0.53730.630000.206315.8379
0.29090.840000.201215.8379
0.33171.050000.201715.9300

Framework versions

  • —Transformers 4.26.0.dev0
  • —Pytorch 1.14.0.dev20221208+cu116
  • —Datasets 2.7.1.dev0
  • —Tokenizers 0.13.2