CoolFace
Modelpublic

JunWorks/whisperBase_LoRA_zhTW

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes11downloads
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 Base LoRA tuned zh-TW

DEMO LINK: https://4e766dca651b881c9b.gradio.live

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

  • —Loss: 0.3839
  • —CER: 22.13% :(

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
0.39811.014530.4017
0.40162.029060.3960
0.35433.043590.3933
0.36384.058120.3905
0.39535.072650.3895
0.3776.087180.3879
0.36467.0101710.3869
0.35928.0116240.3860
0.33249.0130770.3853
0.381810.0145300.3848
0.310711.0159830.3844
0.347312.0174360.3844
0.368413.0188890.3845
0.388614.0203420.3841
0.365215.0217950.3839

Framework versions

  • —PEFT 0.9.1.dev0
  • —Transformers 4.39.0.dev0
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.18.0
  • —Tokenizers 0.15.2