CoolFace
Modelpublic

Gummybear05/whisper-small-E10_speed_pause2

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes10downloads
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-E10Ypausespeed

This model is a fine-tuned version of openai/whisper-small on the aihub old adult freq speed pause changed dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2311
  • Cer: 6.8433

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: 8
  • seed: 42
  • gradientaccumulationsteps: 2
  • totaltrainbatch_size: 16
  • optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • lrschedulertype: linear
  • lrschedulerwarmup_steps: 50
  • num_epochs: 2
  • mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossCer
0.26510.12891000.27226.8961
0.13540.25792000.25586.7199
0.14720.38683000.25416.6377
0.10870.51584000.24606.6964
0.10410.64475000.24986.9079
0.08570.77376000.24206.6729
0.08410.90267000.23796.3910
0.03511.03098000.23716.3616
0.03051.15999000.23406.3851
0.02781.288810000.23766.1266
0.03041.417811000.23387.0312
0.03211.546712000.23757.1487
0.02931.675713000.23606.9666
0.03021.804614000.23337.2368
0.03421.933615000.23116.8433

Framework versions

  • Transformers 4.47.0.dev0
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3