CoolFace
Modelpublic

Pageee/DistilFT-Frisian-10md

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes3downloads
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. -->

DistilFT-Frisian-10m

This model is a fine-tuned version of distil-small.en on the mozilla-foundation/commonvoice6fyNL dataset. It achieves the following results on the evaluation set:

  • —Loss: 4.1946
  • —Wer: 89.3637

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: 0.0001
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 200
  • —training_steps: 3000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
0.115433.33335003.7440105.5534
0.010766.666710004.081488.1911
0.0100.015004.131490.7432
0.0133.333320004.170089.8663
0.0166.666725004.187889.6061
0.0200.030004.194689.3637

Framework versions

  • —Transformers 4.41.0.dev0
  • —Pytorch 2.3.0+cu121
  • —Datasets 2.19.1
  • —Tokenizers 0.19.1