CoolFace
Modelpublic

patipol-bkk/whisper-tiny-alphadigit-decoder-finetune-10k-clean

sourceHugging Faceapache-2.0updated 3y 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. -->

Whisper Tiny AlphaDigit Decoder Finetune 10k Clean

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

  • —Loss: 0.0615
  • —Wer: 58.8931

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: 32
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 500
  • —training_steps: 10000

Training results

Training LossEpochStepValidation LossWer
0.09870.5110000.087890.7605
0.07451.0320000.073791.3320
0.06471.5430000.068983.4997
0.0632.0540000.067679.2696
0.04982.5650000.065569.8125
0.05113.0860000.063469.5636
0.03733.5970000.062365.4287
0.03614.180000.061961.4768
0.04654.6190000.061759.5491
0.03765.13100000.061558.8931

Framework versions

  • —Transformers 4.33.0.dev0
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.14.4
  • —Tokenizers 0.13.3