CoolFace
Modelpublic

octava/whisper-small-ablation-add-NLD-80

sourceHugging Faceapache-2.0updated 5mo 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-ablation-add-NLD-80

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

  • —Loss: 0.4274
  • —Wer: 17.0206

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: 1000

Training results

Training LossEpochStepValidation LossWer
0.35310.46732000.426218.9012
0.27990.93464000.462318.4440
0.18291.40196000.434518.7094
0.18411.86928000.421517.1976
0.0912.336410000.427417.0206

Framework versions

  • —Transformers 4.45.0
  • —Pytorch 2.11.0+cu130
  • —Datasets 3.0.1
  • —Tokenizers 0.20.0