CoolFace
Modelpublic

MelanieKoe/w2v2-base-pretrained_lr5e-5_at0.3_da1

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes7downloads
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. -->

w2v2-base-pretrainedlr5e-5at0.3_da1

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.4352
  • —Wer: 0.1704

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: 32
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_steps: 1000
  • —training_steps: 4000
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWer
19.67253.972504.94091.0
3.50437.945003.24141.0
3.116211.97503.13511.0
2.213815.8710000.91460.9184
0.530819.8412500.62920.4357
0.276223.8115000.87130.2384
0.189427.7817500.95370.1905
0.133931.7520001.23550.1824
0.100235.7122501.21930.1739
0.085839.6825001.15570.1709
0.071143.6527501.35910.1692
0.058947.6230001.33720.1683
0.052551.5932501.41330.1683
0.046455.5635001.49690.1679
0.043659.5237501.42620.1674
0.040163.4940001.43520.1704

Framework versions

  • —Transformers 4.35.0
  • —Pytorch 2.0.0
  • —Datasets 2.14.6
  • —Tokenizers 0.14.1