CoolFace
Modelpublic

JunWorks/whisperSmall_LoRA_zhTW

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes3downloads
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 LoRA tuned zh-TW

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2094
  • —CER: 13.1583%

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: 8
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —num_epochs: 15
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.22841.014530.2305
0.22212.029060.2183
0.19393.043590.2149
0.20854.058120.2125
0.22025.072650.2112
0.20976.087180.2103
0.20727.0101710.2095
0.19068.0116240.2094
0.18189.0130770.2091
0.205410.0145300.2093
0.159711.0159830.2094
0.179712.0174360.2095
0.20413.0188890.2096
0.187214.0203420.2094
0.187915.0217950.2094

Framework versions

  • —PEFT 0.9.1.dev0
  • —Transformers 4.40.0.dev0
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.18.0
  • —Tokenizers 0.15.2