CoolFace
Modelpublic

maratos/checkpoints_1

sourceHugging Faceapache-2.0updated 2y 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-arpa

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

  • —Loss: 0.0186
  • —Wer: 2.9762
  • —Cer: 1.0999

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-05
  • —trainbatchsize: 16
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 1000
  • —num_epochs: 1
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepCerValidation LossWer
0.05290.571650003.55320.04947.8609
0.0281.1432100005.56560.04139.7632
0.02981.7149150002.99260.03506.4210
0.01332.2865200002.18960.03225.0360
0.01052.8581250002.07950.03074.7797

Framework versions

  • —Transformers 4.42.3
  • —Pytorch 2.3.1+cu121
  • —Datasets 2.20.0
  • —Tokenizers 0.19.1